How WhatsApp is fighting spam after its encryption

WhatsApp proved itself to be the most YOLO-crypto company of 2016 when it turned on end-to-end encryption by default last April for its more than 1 billion users. (Facebook, WhatsApp’s parent company, took a more cautious approach when it added opt-in encryption to Messenger.) But WhatsApp’s all-in approach has come at a cost — the company’s executives were arrested and its service was temporarily shut down in Brazil when local courts demanded that WhatsApp turn over the contents of encrypted messages.

Rolling out end-to-end encryption raised not just political concerns, but practical ones. If WhatsApp couldn’t read the contents of its users’ messages anymore, how would it detect and fight spam on the platform? WhatsApp could have become a haven for scammers pushing pills and get-rich-quick schemes, which would have driven users off the platform and harmed its business even more than short-term court-ordered shutdowns.

Instead, WhatsApp developed approaches to detecting spam that don’t rely on content at all, says WhatsApp engineer Matt Jones. Instead of looking at message content, WhatsApp analyzes behavior for indications that a user might be spamming. The approach is working surprisingly well. Jones says that WhatsApp slashed spam by 75 percent after launching end-to-end encryption.

“If you have well-instrumented behavioral features, it’s totally possible to detect spam without any access to message content in an end-to-end encrypted world,” Jones said at the USENIX Enigma security conference yesterday.

Some of WhatsApp’s behavioral detection systems will sound familiar to anti-spam experts. For instance, WhatsApp looks at how many messages a user is sending and will flag as spam if the user is sending an unusually high number of messages per minute, a common anti-spam strategy. But WhatsApp also uses a number of other signals to determine the probability that a message contains spam.

“The simplest approach is to look at the reputation of the things an actor is using,” Jones explained. WhatsApp examines data related to the internet service provider (ISP), the phone number, and the phone network being used, and compares that to previous spam reports. If the ISP data or the phone prefix (the first several digits of a phone number) have been previously associated with spammers, it’s likely that messages associated with that data are still spam. WhatsApp will also take notice if, for example, a phone with a Canadian country code connects via a cell network in Thailand and assess the probability that the user is a spammer or a traveller on vacation.

Once a spammer is reported, WhatsApp will also go back and look at the spammer’s actions on the platform for clues about why he wasn’t caught, then feed that information into its model. “Every message they sent before was an opportunity to prevent spam that we failed to take,” Jones said.

WhatsApp bans users based on these probabilistic models, and if the company makes a mistake, users can appeal the ban. Jones said that WhatsApp has also cut back on mistaken bans through its enhanced spam detection. “We cut spam by three quarters and the number of incorrect bans by half,” he said.

“The goal is to drive up the cost for attackers,” Jones added. “Eventually we’re going to catch all spammers. If you send spam, you’re going to be reported and if you’re reported, you’re going to be banned.”

However, this approach relies heavily on the analysis of metadata (the non-content information associated with transmitting a message), and WhatsApp has been criticized for hanging on to users’ metadata and sharing it with Facebook. End-to-end encryption only guarantees the privacy of message content, not metadata, but many non-technical users might not understand the difference and may be surprised to learn how WhatsApp collects and analyzes their information.

Open Whisper Systems, the maker of the encrypted chat app Signal and the Signal Protocol (on which WhatsApp’s encryption is based) recently released its first subpoena and its response. The documents showed that OWS doesn’t keep metadata on its users — all that the company could hand over was the account creation date and the last log-in time.

Harvesting metadata is a trade-off. As OWS grows, it may find itself struggling with a spam problem. And WhatsApp will have to balance users’ expectations of privacy with their demand for a spam-free experience. Jones told TechCrunch that it’s a balance he thinks about often. He said the company has chosen to dump certain categories of metadata that proved unhelpful for spam prevention so as not to unnecessarily retain user info.

Some firms are hesitant to implement end-to-end encryption because they worry it will prevent them from fighting spam or rolling out new features, but the spam-prevention success that Jones described might encourage other communications companies to take the encryption plunge

Twitter Staff Give $1m to Fight Trump Travel Ban

Staff at social media company Twitter have donated more than $1m (£790,000) to the American Civil Liberties Union.

The ACLU has pledged to fight President Donald Trump's temporary ban on refugees and immigrants from seven Muslim-majority countries.

The civil rights group has reportedly raised more than $24m in online donations in the past few days.

Taxi hailing company Lyft previously said that it would donate $1m to the ACLU over the next four years.

Nearly 1,000 Twitter employees donated more than $500,000, which was matched by chief executive Jack Dorsey and executive chairman Omid Kordestani, according to TechCrunch.

In an email sent to Twitter staff and obtained by the tech news website, lawyer Vijaya Gadde said: "Our work is far from done.

"In the coming months we'll see a flurry of legal challenges, legislative pushes and public pronouncements.

"But as long as civil liberties are threatened, I'm proud to know that as individuals we will stand up to defend freedom and look after people."

It is also reported by Bloomberg that some of the largest US technology companies are preparing an open letter to President Trump, expressing concern about his order on immigration and offering help to "fix it".

Meanwhile, messaging platform Viber has offered free international calls to the affected countries - Iraq, Syria, Iran, Libya, Somalia, Sudan and Yemen

SMARTWATCH THAT CAN TELL EMOTION

Anyone who’s been on a first date knows that trying to read a total stranger’s emotions is completely bewildering. We all know story could be interpreted in a multitude of ways — telling your friend about your awesome new phone can come across as excitement or a brag, depending on the listener. To help detect the sentiment behind speech, a team at the Massachusetts Institute of Technology built a wearable app that can parse conversation to identify the emotion behind each part of the story.

The app, built into a fitness tracker for this research, collects physical and speech data to analyze the overall tone of the story in real time. Using artificial intelligence, the app can also figure out which part of the conversation was happy or sad, and tracks emotional changes in five-second intervals.

In the research, participants were asked to wear a Samsung Simband with the app installed and tell a story. The band also monitored the participants’ physical changes, such as increased skin temperature, heart rate, or movements such as waving their arms around or fidgeting. Overall, the neural networks were able to determine tone with 83 percent accuracy — though it is unclear whether the research has been peer-reviewed.

Generally, the AI associated parts of speech that had long pauses or used monotonous vocal tones as sad, while varied speech patterns were categorized as happy. The team hopes to label more complex emotions soon.

“Imagine if, at the end of a conversation, you could rewind it and see the moments when the people around you felt the most anxious,” said graduate student Tuka Alhanai, who is part of the research team. The product could be used to help those with anxiety or conditions like Asperger’s or autism. “Our work is a step in this direction, suggesting that we may not be that far away from a world where people can have an AI social coach right in their pocket.”

The research is an ongoing effort from MIT’s Computer Science and Artificial Intelligence Laboratory to study emotion detection. Last fall, the team built a device to identify human emotions using wireless signals.

Ecobank launches US$500,000 Fintech Challenge

Ecobank Fintech Challenge is a pan-African innovation competition and start-ups partnership offering by Ecobank. It is designed to inspire, support and partner African start-ups and developers with the aim to facilitate the development of innovative “FinTech” and banking related solutions.

Ecobank is challenging Africa’s new generation of entrepreneurs to find lasting solutions to the continent’s most pressing banking issues. Submit entries in one or more of our key areas of interest for your Chance to win up to $500,000 funding.

The Ecobank Fintech Challenge will have startups submit applications addressing specific fintech challenges. Shortlisted applicants will get to pitch their idea at the Ecobank Innovation Fair for the chance to win cash prizes and get support from Ecobank to roll out their solution across 36 African countries. They’ll also get mentoring opportunities and have access to Ecobank’s vast network of partners.

If you’re interested in entering the competition, you can apply online.  Submit your solution to a fintech challenge in any of the areas listed on the dedicated website for the contest. Applications will be judged based on user experience, implementation practicality, functionality, innovation, and commercial prospects.

If you’re interested in entering the competition, you can apply online.  Submit your solution to a fintech challenge in any of the areas listed on the dedicated website for the contest. Applications will be judged based on user experience, implementation practicality, functionality, innovation, and commercial prospects.

Only entries that are adjudged to have met the selection criteria will be shortlisted for the pitch stage.

Applications will be received until April 14, 2017.

To register for the Ecobank Fintech Challenge, click here.

Lagos to join global UN SDG Hackathon

UK-based charity Influx Trust is to host a global hackathon around the United Nations’ (UN) Sustainable Development Goals (SDGs), with applications currently open to the Lagos edition of the event.

For 48 hours over March 10 to 12, nine hackathons will be held simultaneously around the world, with each location hacking around one of three selected SDGs.

The Lagos-based hackathon will focus on SDG 9, and looks for solutions in the areas of industry, innovation, and infrastructure.

The winning teams from each regional event will be given resources and support by the UN to hone, test and scale their ideas into sustainable businesses. They will also have a chance to demo their solutions at the UN headquarters in New York, in June 2017.

Solutions emerging from the hackathon will also be placed on the Influx Trust crowdfunding page, to attract investors, mentors, and human resources.

“For the first time in our history, we are at a point where we have the tools, ideas and technology to solve the world’s problems and have a real impact on the UN’s Sustainable Development Goals,” said the Influx Trust.

“It has become commonplace thinking that government cannot and should not be expected to solve all our problems and it is up to us to work together to build the future we need and help the the UN achieve it’s goals.”

The Lagos hackathon is hosted by Passion Incubator, Ford Foundation, Microsoft, Printivo and Starta; and will be held at the Ford Foundation in Ikoyi.

Registration is available here, until March 3