African traffic growth and predictions for the future

African traffic growth and predictions for the future

Looking back at our historical data, we realized how much the Internet and Cloudflare grew. With more than 150 datacenters, 10 percent of web-based applications, customers everywhere around the world, from the tiny islands in the Pacific to the big metropolises, we have an Internet landscape of almost every country and continent.

Cloudflare’s mission is to help build a better Internet. To do that we operate datacenters across the globe. By having datacenters close to end user we provide a fast, secure experience for everyone. Today I’d like to talk about our datacenters in Africa and our plans to serve a population of 1.2 billion people over 58 countries.

Internet penetration in developed countries skyrocketed since the 2000s, Internet usage is growing rapidly across Africa. We are seeing a 4% to 7% increase in traffic month on month. As of July 2018, we have 8 datacenters on the African Continent:

  • Angola
  • Djibouti
  • Egypt
  • Kenya
  • Mauritius
  • Three in South Africa

While we see changes on the horizon, the majority of Internet content providers are located in North America and Western Europe. This means that only the billion people living in those areas close to the content they are trying to reach. When it comes to Africa, submarine cables will usually bring back the packets to Europe to hubs like Marseille, Paris, London, Lisbon and sometimes Frankfurt or Amsterdam, adding precious milliseconds, slowing down communications.
By setting up datacenters on the African continent, Cloudflare is able to serve content locally, increasing download speed in the region, improving the end-user experience, and ultimately increasing Internet usage.

Growth of a continent

We wondered if the Internet usage increased when we set-up a datacenter in a region which was previously not well served.
It was surprising to see a fast growth in the following months in each of the countries we turn on our equipment. We took into account bandwidth and also quantity of information exchanged. The increase in bandwidth usually leads to an increase in usage.

Why is bandwidth increasing with lower latency?
Bandwidth is the maximum rate information can be transferred over a link. The interpretation of maximum depends on the type of transmission.
The explanation why the rate is dependent on latency comes from the TCP protocol specification on which run most of the web applications. Every transmission ends with an acknowledgement, to determine if the data was correctly received. The next transmission will begin after the sender receives the acknowledgement. This means while the acknowledgement is transmitting, nothing is actually being received. The difference of data received over time is the transfer rate.
This is summarized in the following diagram:

African traffic growth and predictions for the future

With the most common algorithms, the amount of data sent before an acknowledgment increases until an error appears. Any link will drop packets: whether there is a transmission issue (wireless and perturbations) or a processing issue (router dropping packets to reduce load). This contributes never reaching the maximum bandwidth of a link. This is why above 80 milliseconds latency, performances start to worsen drastically. Coast to coast in the USA is around 70 milliseconds. Paris to London is 10 milliseconds. Satellites connections implement proxies to allow sustainable throughput despite 600 milliseconds round-time-trip.

Why is the amount of requests increasing with higher bandwidth?
The explanation is behavioral. If an Internet connection is slow and frustrating, chances are we will use it only if we are forced to. While getting access to the content immediately, people are likely to fetch more content and click on links.

The following chart shows the growth of requests from a country after every datacenter turn up. Traffic is normalized on the latest value (July 2018).
Djibouti shows the biggest increase in traffic after the launch.

African traffic growth and predictions for the future

For the rest of the continent, we are seeing a steady increase in delivered traffic over the last four years.

Overall, Sierra Leone is the country which grew the most at around 8% per month. At the opposite scale, Algeria only increased its traffic by 2% per month. The mean of all those countries is 6.2% per month, which is also the Internet traffic growth of South Africa.

African traffic growth and predictions for the future

In comparison to Europe, North America, it will take, at the current rate, 4 years and 3 months for Africa to reach today’s traffic levels of those two continents. However, if Europe, North America keeps its current 4% growth rate, then the African continent will take approximately eight to twelve years to catch up.

Please note these estimations are not perfectly representative as Cloudflare only see a part of the Internet and the numbers also includes our growing base of customers.

African traffic growth and predictions for the future

The units on the vertical axis represent the growth based on the initial ratio between Europe/USA/Canada and Africa.

Latencies and inter-African routing

We analyzed the latencies between Europe and African IP addresses that hit our edge. On the following Demer map from Vasco Asturiano, the area of the country is exponentially proportional to the response time in milliseconds.

African traffic growth and predictions for the future

All the coastal Africa is well connected with submarines cables. The only exception is Eritrea, where the main provider (EriTel) which uses two satellite providers for its outbound links.
The island of Saint Helena is on the path of the future SAex cable, but the only connection at the moment for its 5000 inhabitants is through satellite, causing a latency of 600ms.
Central African Republic also uses satellite or connections through Cameroon.

On average a packet round trip from Northern Africa to Europe will take around 50-100ms while a round trip from the South will take 250ms.

Regarding inter-African routing, Africa has only a limited number of cities where interconnection happens successfully: Johannesburg in South Africa, Nairobi in Kenya, and Djibouti with datacenters and internet exchange points. The rest of the continent is mostly split between providers which will interconnect in Europe or Asia. Chances are, a user in Cameroon talking to a user in Ghana will likely go through Paris.
Using RIPE Atlas, we are able to show inter-provider routing usually happens in Europe. Only one traceroute showed packets being exchanged in South Africa.

Traceroute to two Ghana Atlas probes from other Atlas Probes

To Ghana only via Europe
To Ghana with one through South Africa

African traffic growth and predictions for the future
African traffic growth and predictions for the future

Cloudflare and many network operators are using extensively RIPE Atlas to determine performance and troubleshoot issues. If you want to help us improve Internet quality in Africa, become a probe host here.

What you may be wondering is: what are the countries in Europe that route the African traffic? We are using an anycast network ; when a user fetch a website on Cloudflare, the packets will take the shortest path seen by the router to reach its destination. In telecommunications, the shortest path does necessarily mean geographical proximity. The selection metric of a path usually involve cost and performance.

African traffic growth and predictions for the future

An anycast address will have the same metric everywhere on our side. This mean a service provider having links to London and Paris will see our IP addresses originating from London datacenter and Paris datacenter. The choice between the two will only be depending on metrics set by the provider: will it cost more to reach London?

Cloudflare has a significant number of points of presence to be able to show small metric differences. Due to the density of its network in Europe, it is common to have datacenters one hop away from each others (London and Paris, Paris and Amsterdam). Our analysis of the next-hop will show a provider’s preference.

In the case of Africa, a provider can rent capacity on submarine cable to a city, for instance Lisbon, Paris, London. Ideally, the provider wants to maximize the resources it can obtain without adding more hops (costlier). Paris, London, Amsterdam and Frankfurt have a lot of content providers and interconnections options, the differences are going to be on the content. One major bias will be the language: France will have more francophone content hosted in Parisian datacenters, it also helps running operations to if both parties speak French.
As an example case: if Paris is chosen, for the content that can only be found in London, another provider will carry the packets to London from Paris, adding one hop to the path, reducing preference. We will see the landing point in Paris.
Why isn’t the provider getting a link to London? On thing to know is any Internet link has a flat rate price plus a variable rate based on consumption.
Bandwidth within major European cities is among the cheapest in the world. The flat rate for submarine capacity is high, as a result, the quantity of content that is available from London for cheaper than Paris has to make up the difference
If you are interested to know more about the costs of bandwidth around the world, check out this article by Nitin Rao.

The following map represents the most common Cloudflare datacenter reached for each country. The countries filled with color are where Cloudflare datacenters are. The border color indicates the destination country.
As aforementioned, we can notice most of the French-speaking countries will tend to go towards our datacenter in Paris. South Africa remains well connected with its neighbors.

African traffic growth and predictions for the future

Where is the content hosted?

Previously, we mentioned there are some content providers in South Africa and Djibouti. We took a look at the popular news and banking websites.

Over the top 200 origins of the websites (Alexa ranking) for African countries in 2017, only 42 were attached to an African country and only 10 among those were serving non-education/government content (news websites, banks).They were located mostly in South Africa and Zimbabwe.

We also took a look at our 10 millions zones behind Cloudflare. The ones that are using Afrinic IPs are hosted in the following countries:
African traffic growth and predictions for the future

What about IPv6?

Only four countries out of sixty four are using IPv6 in a measurable way. Egypt (1%), Kenya (2%), Gabon (2%) and Zimbabwe (9%). In each of these countries we found that only one provider that deployed IPv6 at any significant scale. Since the beginning of the year, IPv6 usage in Egypt has doubled. In Gabon, a major provider rolled IPv6 at the end of December 2017. As Mathieu Paonessa from Group Vivendi Afrique told us, “Gabon went from 0% to 2% IPv6 in only 9 months, following the opening of our CanalBox Gabon FTTH service.”

The timeline is similar with a small ISP in Kenya and has been increasing steadily. We can maybe hope they double their IPv6 usage by the end of 2018.

Compared to the rest of the world, Belgium is still ahead with 37%, followed by India at 35%. Most European countries are above 10%. USA is 22% and Canada is 15%.

One explanation for the small number of deployments is the size of the remaining IPv4 pool of addresses.
As of July 2018, there were 36,245 /24 available (approximately 9.2 millions IPs). The total Afrinic size is 6 /8 (approximately 100 millions IPs). 9% are left.
The following graphs shows the allocations and usage of each /24 in the Afrinic allocations.
This is the Hilbert graph of Afrinic IPv4 exhaustion. It was inspired by Ben Cartwright-Cox’s blog post and used masscan and ipv4-heatmap.

Prefix
Announced (yellow) vs Available (green) vs Reserved (red)
Response to ICMP (blue = low reply, red = all reply)

41.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

102.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

105.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

154.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

196.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

197.0.0.0/8
African traffic growth and predictions for the future
African traffic growth and predictions for the future

We notice that even if allocated, some blocks remain dark. 102.0.0.0/8 remains the range with the most IP space left in the world.

More deployments coming soon

Africa is the largest continent on earth, yet it is very lagging behind on Internet connectivity and traffic levels. Historically it’s been entirely relying on its European interconnections. However we predict that its traffic will outgrow EU and US by 2027. This will be enabled by the fast deployment of local content, IPv6, and alternative submarine cables.

We are working on deploying even more points of presence in Africa and increasing our current capacity in the existing ones. Fifteen new locations in the African continent are part of our global expansion plans. These include: Algeria (Algiers), Cameroon (Yaoundé), Congo (Kinshasa), Côte d’Ivoire (Abidjan), Egypt (Alexandria), Ghana (Accra), Kenya (Nairobi), La Réunion (Sainte-Marie), Madagascar (Antananarivo), Morocco (Casablanca), Nigeria (Lagos), Tanzania (Dar es Salaam), Tunisia (Tunis), Uganda (Kampala), and Zimbabwe (Harare)

African traffic growth and predictions for the future

Header image source

Source:: CloudFlare

BT and Axione Lock Horns Over Scotland’s R100 Broadband Plan

scotland r100 suppliers leak

The Scottish Government’s future £600m R100 (Reaching 100%) superfast broadband rollout programme could be facing a problem after sources told ISPreview.co.uk that Axione, one of three remaining bidders for the contract, had allegedly set its lawyers on BT (Openreach) over claims of anti-competitive behaviour. At the time of writing Openreach and Axione have both informed […]

Source:: ISPreview

Uber: Expands in Africa, South America – but haemorrhaging money

Frictionless transport company Uber has announced plans to expand its ride-hailing service to two more East African countries before the end of the year, via its Chap Chap business, which currently operates in Kenya.

Uber piloted the low-cost service in the capital, Nairobi, and now operates 400 fuel-efficient Suzuki Altos in the city.

In Kenya, Uber competes with Taxify, Little, and Mondo Ride, and operates in partnership with local telco, Safaricom. Further details of the East Africa expansion scheme have not been provided.

In Nigeria, public support for Uber’s ride-hailing service is rising, with the company reporting monthly passenger numbers of 267,000 this week.

In the Middle East, Uber has been in talks with local rival Careem to combine ride-hailing services in the region, in the run-up to Uber’s planned IPO next year.

However, news earlier this year that market regulators in Singapore are acting against its merger with local rival Grab may damage the prospects of further deals that reduce regional competition.

Safety first

Uber has also announced that it is opening a $64 million safety technology centre in Sao Paulo, Brazil, to develop systems to improve rider and driver safety in South America.

Uber’s app provides more rides in the city than anywhere else in the world.

The office will open this year and the investment will unfold over a five-year period, said the company.

Losses ramp up

Despite the positive news, Uber this week reported a Q2 adjusted EBITDA loss of $404 million – an increase of 31 percent on the previous quarter, and up on the same period last year. Revenues were up 49 percent.

Sequential losses have persuaded some Uber investors to call for the sell-off of its self-driving car unit, which has contributed 15-30 percent of the company’s total losses each quarter.

The company announced in July that it was closing its driverless truck division to focus on cars. It also trailed a possible tie-up with autonomous tech rival, Waymo.

Investors are worried that the planned IPO may be damaged by rising losses, especially those spurred by a division that will have to fund expensive technology development for many years to come, against rivals such as GM, Ford, Tesla, and Waymo.

  • Read more: Musk at bay: Will Saudi cash help Tesla rid the world of oil?

Internet of Business says

Earlier this year, Uber repositioned itself as an Amazon-style hub for all forms of connected transport, from ride-hailing and electric bike hire to public transport ticketing.

The company is also developing a pilotless air taxi concept.

However, whether the company can sustain a focused global business in connecting users with frictionless transport while at the same time pouring money into developing autonomous vehicles on the road and in the sky must be in doubt, if investors withdraw their backing.

Public support for driverless cars has fallen in the US, in the wake of Uber’s fatal crash in March, and the Tesla accident just days later, in which a driver died while his vehicle was operating under software control.

  • Read more: Uber closing self-driving truck division, refocusing on cars
  • Read more: Uber’s Grab merger may be undone, threatening new Middle East deal
  • Read more: Musk at bay: Will Saudi cash help Tesla rid the world of oil?

The post Uber: Expands in Africa, South America – but haemorrhaging money appeared first on Internet of Business.

Source:: Internet of Business

Indian Bank Hit in $13.5M Cyberheist After FBI ATM Cashout Warning

On Sunday, Aug. 12, KrebsOnSecurity carried an exclusive: The FBI was warning banks about an imminent “ATM cashout” scheme about to unfold across the globe, thanks to a data breach at an unknown financial institution. On Aug. 14, a bank in India disclosed hackers had broken into its servers, stealing nearly $2 million in fraudulent bank transfers and $11.5 million unauthorized ATM withdrawals from more than two dozen cash machines across multiple countries.

The FBI put out its alert on Friday, Aug. 10. The criminals who hacked into Pune, India-based Cosmos Bank executed their two-pronged heist the following day, sending co-conspirators to fan out and withdraw a total of about $11.5 million from 25 ATMs in Canada, Hong Kong and India.

The FBI warned it had intelligence indicating that criminals had breached an unknown payment provider’s network with malware to access bank customer card information and exploit network access, enabling large scale theft of funds from ATMs.

Organized cybercrime gangs that coordinate these so-called “unlimited attacks” typically do so by hacking or phishing their way into a bank or payment card processor. Just prior to executing on ATM cashouts, the intruders will remove many fraud controls at the financial institution, such as maximum withdrawal amounts and any limits on the number of customer ATM transactions daily.

The perpetrators alter account balances and security measures to make an unlimited amount of money available at the time of the transactions, allowing for large amounts of cash to be quickly removed from the ATM.

My story about the FBI alert was breaking news on Sunday, but it was just a day short of useful to financial institutions impacted by the breach and associated ATM cashout blitz.

But according to Indian news outlet Dailypionneer.com, there was a second attack carried out on August 13, when the Cosmos Bank hackers transferred nearly $2 million to the account of ALM Trading Limited at Hang Seng Bank in Hong Kong.

“The bank came to know about the malware attack on its debit card payment system on August 11, when it was observed that unusually repeated transactions were taking place through ATM VISA and Rupay Card for nearly two hours,” writes TN Raghunatha for the Daily Pioneer.

Cosmos Bank was quick to point out that the attackers did not access systems tied to customer accounts, and that the money taken was from the bank’s operating accounts. The 112-year-old bank blamed the attack on “a switch which is operative for the payment gateway of VISA/Rupay Debit card and not on the core banking system of the bank, the customers’ accounts and the balances are not at all affected.”

Visa issued a statement saying it was aware of the compromise affecting a client financial institution in India.

“Our systems were able to identify the issue quickly, enabling the financial institution to take appropriate action,” the company said. “Visa is working closely with the client in supporting their ongoing investigations on the matter.”

The FBI said these types of ATM cashouts are most common at smaller financial institutions that may not have sufficient resources dedicated to staying up to date with the latest security measures for handling payment card data.

“Historic compromises have included small-to-medium size financial institutions, likely due to less robust implementation of cyber security controls, budgets, or third-party vendor vulnerabilities,” the alert read. “The FBI expects the ubiquity of this activity to continue or possibly increase in the near future.”

In July 2018, KrebsOnSecurity broke the news of two separate cyber break-ins at tiny National Bank of Blacksburg in Virginia in a span of just eight months that led to ATM cashouts netting thieves more than $2.4 million. The Blacksburg bank is now suing its insurance provider for refusing to fully cover the loss.

As reported by Reuters, Cosmos Bank said in a press statement that its main banking software receives debit card payment requests via a “switching system” that was bypassed in the attack. “During the malware attack, a proxy switch was created and all the fraudulent payment approvals were passed by the proxy switching system,” the bank said.

Translation: If a financial institution is not fully encrypting its payment processing network, this can allow intruders with access to the network to divert and/or alter the response that gets sent when an ATM transaction is requested. In one such scenario, the network might say a given transaction should be declined, but thieves could still switch the signal for that ATM transaction from “declined” to “approved.”

One final note: Several news outlets have confused the attack that hit Cosmos Bank with another ATM crime called “jackpotting,” which requires thieves to have physical access to the inside of the cash machine and the ability to install malicious software that makes the ATM spit out large chunks of cash at once. Like ATM cashouts/unlimited operations, jackpotting attacks do not directly affect customer accounts but instead drain ATMs of currency.

Source:: KrebsOnSecurity

Kernel of Truth episode 5.5 — Greg Farro talks Voyager

Subscribe to Kernel of Truth on iTunes, Google Play, Spotify, Castbox and Stitcher!

Click here for our previous episode.

If you enjoyed our previous episode about hyper-converged infrastructure, then you’re in for a real treat — the infamous Greg Ferro of Packet Pushers is back for a special BONUS episode of Kernel of Truth! We learned that once you get Greg and JR talking, it’s nearly impossible to get them to stop. So, we let them keep going and recorded an extra episode all about Voyager. Greg’s got questions about our open packet optical platform, and JR’s got answers. You’ll be impressed with how much awesome info and discussion they can fit into a mini episode!

Like what you’re hearing and want to talk about it with fellow Kernel of Truth fans? Good news! We’ve got a new Cumulus community forum for the podcast where you can chat with other podcast and networking aficionados. Be sure to check it out!

As always, you can tweet any questions, feedback or topics you want us to discuss at @cumulusnetworks and use the hashtag #KernelOfTruth — we want to hear from you, and give you content that you want to hear!
Guest bios

Greg Ferro: Greg is a household name in the tech industry as a co-founder of Packet Pushers. He survived 25+ years of Enterprise IT as a network engineer, architect and designer. Hear him on the Weekly Show, Priority Queue, and Network Break. You can follow him on Twitter at @etherealmind

JR Rivers: JR is a co-founder and CTO of Cumulus Networks where he works on company, technology, and product direction. JR’s early involvement in home-grown networking at Google and as the VP of System Architecture for Cisco’s Unified Computing System both helped fine tune his perspective on networking for the modern datacenter. Follow him on Twitter at @JRCumulus

Episode 5.5 links

Packet Pushers Twitter: @packetpushers

Cumulus Twitter: @cumulusnetworks

Slack: slack.cumulusnetworks.com

Kernel of Truth forum: https://forums.cumulusnetworks.com/kernel-of-truth-podcast-232118

Website: cumulusnetworks.com

More about Voyager: https://cumulusnetworks.com/products/voyager/

The post Kernel of Truth episode 5.5 — Greg Farro talks Voyager appeared first on Cumulus Networks Blog.

Source:: Cumulus Networks

IBM, Maersk launch blockchain-based shipping platform with 94 early adopters

After launching a proof of concept earlier this year, IBM and Maersk have unveiled TradeLens, the production version of an electronic ledger for tracking global shipments; the companies say they have 94 participants piloting the system, including more than 20 port and terminal operators.

The jointly developed electronic shipping ledger records details of cargo shipments as they leave their origin, arrive in ports, are shipped overseas and eventually received.

To read this article in full, please click here

Source:: IT news – Security

Chirp brings audio solution to Microsoft Azure for IoT onboarding

chirp agree deal with microsoft for azure iot provisioning

NEWSBYTE Acoustic networking specialist Chirp has convinced Microsoft to integrate its technology into the Azure Cloud, paving the way for the simpler provisioning of new IoT devices.

Chirp’s technology converts data into a soundwave (or ‘chirp’) that can be be picked up by any nearby device fitted with a microphone.

Microsoft’s move will lower Azure provisioning times for IoT devices down from minutes to a matter of seconds, according to Chirp CTO James Nesfield.

  • Read more: Chirp: Why transmitting data as sound waves could transform IoT networking | Exclusive CTO Q&A

Changing the way IoT devices are provisioned

Adding a smart device to a new Wi-Fi network is often a long-winded process. Provisioning one on the Azure Cloud usually requires several minutes as users turn their device into a WiFi hotspot, connect to it using a laptop or smartphone, and set up its credentials.

Microsoft’s new provisioning system for IoT devices uses Chirp technology to convert the device’s credentials into sound and broadcast it from the speaker of a laptop or phone. A nearby offline device running the Chirp Arm SDK (see below) receives the data as audio and uses the encoded credentials to connect to the network and authenticate the connection.

A demo of the solution in action can be seen here:

Read more: Chirp and EDF Energy team up on power station connectivity project

Internet of Business says

Following the announcement, Chirp has released a free SDK for the Azure MXChip board.

“This is a big milestone for data over sound,” said CTO James Nesfield. “It marks the first public release of the Chirp SDK for Arm processors.

“We’ve harnessed the power of Arm’s CMSIS optimised DSP library to enable low-power, real-time Chirp encoding and decoding on the Cortex-M4 and Cortex-M7 chips — which means you can add data-over-sound capabilities to your embedded devices at a sub-dollar cost per unit.”

The post Chirp brings audio solution to Microsoft Azure for IoT onboarding appeared first on Internet of Business.

Source:: Internet of Business

Public concerns on driverless vehicles up, Ford releases safety report

ford autonomous vehicles - new safety report

There’s little point in developing autonomous vehicles if you can’t also build the trust required with the public to bring about their adoption. That’s the main takeaway from the 2018 Cox Automotive Evolution of Mobility Study.

Autonomous vehicles now seen as more dangerous

The research found that 84 percent of drivers want the option to take control even in a completely self-driving vehicle, and just 16 percent are comfortable letting an autonomous system take full responsibility for a journey.

With recent high-profile accidents involving autonomous systems doubtless in mind, the number of respondents who believe that roads would be safer if all vehicles were fully autonomous has dropped to 18 percent in the past two years.

Despite advances in computer vision technology and millions of test miles driven by companies such as Waymo, Uber, GM, Apple, Tesla, and Ford, self-driving vehicles are now seen as less safe than they were in 2016.

However, the study also suggests that, despite their reservations, consumers still want – and to a degree expect – semi-autonomous safety features. In fact, 54 percent of respondents agreed that semi-autonomous features, such as collision warning and avoidance systems, help to make people better drivers.

This disconnect between perception and reality is where autonomous vehicle manufacturers still have much work to do. “There is a major opportunity, and a real need, for automakers and mobility providers to help educate consumers and further guide autonomous vehicles in their development,” said Joe George, Cox Automotive Mobility Solutions’ Group president.

“Autonomous safety feature adoption will be critical in creating future autonomous technology advocates.”

  • Read more: Ford debuts $4bn driverless division – Uber & Waymo motoring on

A matter of trust: Ford’s approach to autonomous vehicles

In related news, Ford has released a safety report this week, entitled ‘A Matter of Trust‘.

In it, CEO of Ford Autonomous Vehicles, Sherif Marakby, argues that gaining the trust of the public and building confidence in the safety, reliability, and overall experience that Ford’s vehicles provide is paramount.

“We don’t believe that the central challenge in the development of self-driving vehicles is the technology. It’s trust. Trust in the safety, reliability, and experience that the technology will enable,” he writes.

“For all of us, self-driving technology is brand new. There’s a lot of talk about it, but it’s not yet clear how it will impact our lives.”

The report goes on to outline how Ford will apply safety processes to its vehicles and testing procedures alongside Argo AI, the startup in which Ford acquired a majority stake last year.

One aspect of Ford’s push to gain public trust is the strict code that its test drivers have to operate by. The fatal accident involving an Uber vehicle in March is thought to have been caused in part by a distracted safety driver at the wheel, as well as by multiple technology inadequacies.

The Matter of Trust report outlines the robust processes that Ford has put in place, which include safety operators working in teams of two, the use of cellphones only when a vehicle is in ‘Park’, mandatory pre- and post-shift daily briefings, and regular classroom sessions to educate drivers on new software releases and capabilities. Uber has itself rolled out new safety features.

Argo AI also ensures that drivers take a three-phase training programme, covering manual driving training and an introduction to autonomy.

The second way to build trust in autonomous systems, says Ford, is to make them predictable. This means taking on the challenge of developing systems that can adapt to cultural norms.

“Part of earning the public’s trust is to drive the vehicle in ways that other motorists, cyclists, and pedestrians expect. Each city has its own culture and expectations for how vehicles should drive,” says the report.

“That’s why we drive extensively in the actual cities where we will eventually deploy our fleet before we allow the vehicles to drive by themselves. In this way, we learn the roads, the challenging intersections, and the local behaviours, so we can develop the system to operate as people expect.”

  • Read more: Uber closing self-driving truck division, refocusing on cars

Communicating intentions

While driving, we take for granted the possibility of communication between ourselves and other road users. Drivers often flash their headlights to signal that they are giving way to cyclists or other cars, for example.

Part of Ford’s drive to make its autonomous cars predictable and trustworthy is to develop a communal language, a method of communicating intention that will ensure that ordinary road users are never surprised by the behaviour of an autonomous vehicle.

To enable a form of communication between people outside the car and their autonomous vehicle, Ford has designed a light bar that’s placed near the windshield, in a position where pedestrians, cyclists, and other drivers would naturally look to make eye contact with a human behind the wheel.

As Ford’s autonomous vehicles move, the light bar attempts to signal its intentions with different patterns. For example, a white light passes back and forth when the vehicle is yielding. If the vehicle is about to set off, the light blinks rapidly to get the attention of other road users.

But clearly, these kind of communication systems are only useful if the general public knows what they mean. Which is why Ford is keen to start a conversation about global standards and encourage public participation in their creation.

“Our light signals still need to undergo a significant amount of research,” says the report, “but we believe development and adoption of a global standard is critical to support eventual deployment of self-driving vehicles. ”

  • Read more: China’s Baidu integrates Intel safety model into autonomous vehicles

Internet of Business says

While safety concerns about autonomous vehicles have grown in the West – particularly the US – on the back of this year’s fatal accidents, they are not shared in China.

  • Read more: Massive fall of consumer trust in driverless cars, says AAA

Chinese customers are among the world’s most optimistic when it comes to driverless cars, said Ford in its recent 2018 Trends Report.

Eighty-three percent of Chinese people said they are hopeful about the future of autonomous vehicles, according to that document, which was based on a survey of over 9,000 people from nine countries and regions.

Despite not having the US’ deeply ingrained culture of car ownership and the freedom of driving – which has risen to the status of myth in Hollywood films and the lyrics of many songs – China is now the world’s largest car market.

As a result, it faces fewer of the cultural obstacles that the US does in the switchover from driver-controlled and -owned petrol cars to autonomous, on-demand electric transport.

The post Public concerns on driverless vehicles up, Ford releases safety report appeared first on Internet of Business.

Source:: Internet of Business

Google tracking, a fax attack, and a vote of “un-confidence” | Avast

Google may still be tracking you…

Adding to the growing mistrust consumers have about what tech companies do with the data they collect, we learned this week from an Associated Press investigation that Google still tracks and stores your whereabouts even if you turn off “location history” in your privacy settings. It turns out that disabling location history, on Android devices and iPhones, only removes your location from the Google Maps Timeline feature — which shows you where you’ve been in Google’s data — but some Google apps still store your time-stamped location data, in part so they can better target ads based on where you’ve been. The company argues that it makes clear to users how to disable this setting and delete location history. So, what can you do to prevent Google from saving these location markers? First, disable a setting called “Web and App Activity,” which stores a variety of information from Google apps and websites to your Google account. Then, delete your location data in your Google account at myactivity.google.com.

Source:: Avast

China: Google backtracks on censored search as employees rebel

China continues to be both a vast business opportunity and an ethical flashpoint for the technology industry.

Google CEO Sundar Pichai told employees yesterday that the company is “not close to launching a search product” in China, as he stated Google’s determination to do more business in the world’s most populous country.

The announcement came after over 1,000 employees signed a letter demanding transparency on the moral and ethical issues involved with launching a censored version of Google’s search engine in the country.

News broke about Google’s plans on 1 August, when internal documents were sent to The Intercept by a whistleblower, showing that Google has been developing a censored version of its search engine, codenamed Dragonfly, for over a year.

Dragonfly will “blacklist sensitive queries” and block websites not permitted by China’s censors, according to the report.

The employee letter, obtained by The New York Times earlier this week, said that the project and Google’s apparent willingness to comply with censorship requirements raise “urgent moral and ethical issues”.

“Currently we do not have the information required to make ethically informed decisions about our work, our projects, and our employment,” it added.

Google at bay

The protest follows a similar move earlier this year when Google’s employees demanded that the company pull out of the Pentagon’s Project Maven programme to use AI to analyse drone footage. Many believed the defence contract would have the effect of weaponising the technology by using it to identify ‘objects of interest’ (strike targets).

As a result of that internal rebellion – and external criticism – Google announced that it will exit the defence deal next year, when the contract comes up for renewal. Google subsequently published a detailed statement on its ethical development strategy for AI.

But does that ethical strategy apply elsewhere?

Google now founds itself challenged by another chorus of disapproval, this time in its core business: search. As a result, it may now face the difficult choice of forever ceding market dominance to companies such as Baidu, or ignoring its own staff and forging ahead with censored technology.

Co-founder Sergey Brin, who was key to Google’s decision to pull the search engine out of China in 2010 in protest at state censorship, reportedly sounded optimistic at the meeting, though progress is “slow-going and complicated”, he said.

The world’s playpen – or cage?

From 2020 onwards, China will effectively become the world’s biggest AI and connected technology proving ground – bigger even than Facebook – as it introduces a compulsory social ratings and citizen monitoring programme across every facet of people’s lives.

The scheme has the stated intention of fostering good behaviour among citizens and punishing bad – including by removing the right to travel or purchase certain goods for some repeat offenders against state policy.

As a result, Western companies find themselves on the horns of a dilemma: pull out of China in protest at a draconian social engineering and surveillance policy, or do business with the world’s second largest economy and effectively support the scheme.

Internet of Business says

As the trade war rages between China and the US, drawing in trading and political allies of both countries, doing business with China now comes freighted with political intrigue. But that hasn’t deterred some companies.

In July, Siemens AG signed a memorandum of understanding with Alibaba Cloud to develop an Industrial Internet of Things platform in China – a move described by the partners as a “landmark deal for bringing Industry 4.0 solutions to China as the world’s powerhouse of manufacturing”.

Earlier this month, China rolled out a set of national standards for testing smart autonomous vehicles on public roads, in an effort to speed up development and encourage innovation.

China is already the world’s largest car market and is determined to become an automotive superpower in driverless vehicles – alongside AI and robotics. It expects connected cars that include some autonomous functions to account for 50 percent of all new vehicles sold in the country by 2020.

Baidu’s self-driving programme, Apollo, has attracted several international partners, including Ford and Daimler AG, the parent company of Mercedes-Benz.

Chinese customers are among the world’s most optimistic when it comes to driverless cars, said Ford in its 2018 Trends Report, echoing the findings of other recent market analyses.

Eighty-three percent of Chinese people said they are hopeful about the future of autonomous vehicles, according to that report, which was based on a survey of over 9,000 people from nine countries and regions.

The post China: Google backtracks on censored search as employees rebel appeared first on Internet of Business.

Source:: Internet of Business