AI serves not only for good. Adversaries can use it and advance their attacks Facebook apologizes after its AI software labels Black men ‘primates’ in a video featured on the platform Facebook apologized for the error of its AI-based software Facebook representatives expressed their regrets for the company’s artificial intelligence ...
The Adversa team makes for you a weekly selection of the best research in the field of artificial intelligence security Physical Adversarial Attacks on an Aerial Imagery Object Detector Deep neural networks (DNNs) provide significant assistance in processing of aerial imagery taken with the help of earth-observing satellite platforms. However, since ...
Even sophisticated technologies such as artificial intelligence can be fooled Researchers Demonstrate AI Can Be Fooled Bankinfosecurity, August 25, 2021 Researchers at Purdue University have found that smart systems used in image recognition tools can be easily tricked with just a camera, a projector and a PC. The study ...
The Adversa team makes for you a weekly selection of the best research in the field of artificial intelligence security AdvDrop: Adversarial Attack to DNNs by Dropping Information While the human eye can recognize objects without high detail, for example, in cartoons, for DNNs this task is still a problem. ...
Machine learning and artificial intelligence can both be used for bad and for good Fooled AI into ignoring stop signs using a cheap projector The Next Web, August 16, 2021 A new adversarial attack can force the system to see or overlook what the malefactors need. Purdue researchers presented their ...
The Adversa team makes for you a weekly selection of the best research in the field of artificial intelligence security Turning Your Strength against You: Detecting and Mitigating Robust and Universal Adversarial Patch Attack Adversarial patch attack against image classification deep neural networks (DNNs) as within such attacks a malefactor ...
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 ...
The Adversa team makes for you a weekly selection of the best research in the field of artificial intelligence security Poison Ink: Robust and Invisible Backdoor Attack Confirmed that deep neural networks are vulnerable to different types of attacks; among them, backdoor attacks are of the greatest interest to researchers, ...
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 ...
Introducing Universal LLM Jailbreak approach. Subscribe for the latest AI Jailbreaks, Attacks and Vulnerabilities If you want more news and valuable insights on a weekly and even daily basis, follow our LinkedIn to join a community of other experts discussing the latest news. In the world of artificial intelligence (AI), [...]
