Secure AI Weekly

Machine learning has come a long way, but it needs to meet safety criteria Novel Feature Importance-Aware Transferable Adversarial Attacks Dramatically Improve Transferability Synced, August 10, 2021 Researchers have proposed the Feature Importance-Aware Attacks  able so significantly enhance the transferability of adversarial examples. Deep neural networks are increasingly used in ...

In order to test smart systems for strength, sometimes you need the help of a large number of people Twitter uses HackerOne bounties to find biases in its image-cropping AI model The Register, August 2, 2021 Twitter’s bug bounty competition is available through HackerOne, where you can help to improve ...

Knowledge about artificial intelligence and its security needs to be constantly improved NIST Requests Information to Help Develop an AI Risk Management Framework Nist, July 29, 2021 The U.S. The Department of Commerce’s National Institute of Standards and Technology (NIST) solicits information from the public to be used in developing ...

Without proper attention from experts, AI can become a weapon in the hands of attackers Researchers Hid Malware Inside an AI’s ‘Neurons’ And It Worked Scarily Well Vice, July 22, 2021 It is expected that neural networks will become more widespread in the future, and then they can become a ...

The face recognition system opens up a number of possibilities for us, while being extremely vulnerable The real facial recognition threat: Worry about bad actors getting ahold of the data Daily News, July 15, 2021 It’s no secret that face recognition systems still raise a number of questions in society. ...

AI serves not only for good. Adversaries can use it and advance their attacks. AI-based recommendations easy to abuse, warn researchers F-secure, June 24, 2021 We see recommendation solutions based on artificial intelligence almost everywhere: in social media and various services and fields such as music, movies, photo stocks, online ...

GitHub Unveils AI Tool to Speed Development, but Beware Insecure Code Dark Reading, July 1, 2021 As a result of a collaboration between GitHub and OpenAI, an artificial intelligence system called Copilot emerged. The system was originally created in order to offer developers suggestions for code: it is expected that ...

Biased AI can cause significant damage to reputation and business AI Weekly: NIST proposes ways to identify and address AI bias Venture Beat, June 25, 2021 It’s no secret that biased AI can significantly damage public trust in AI.  The National Institute of Standards and Technology (NIST), the U.S. agency ...

One of the main problems of AI is the lack of trust from users Is there any way out of Clearview’s facial recognition database? The Verge, June 9, 2021 Last year it became known that the Clearview AI company used millions of images from the Internet to create a facial ...