Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples — mentioned by visarga

Sat, 03 Feb 2018 04:27:19 GMT

> Letting a computer drive my car is high-risk: If there is a malfunction at 70mph, I could die! Google can't even make GPS mapping work perfectly - it's apparent if you use it for a day. Not to mention that AI vision systems are susceptible to adversarial attacks, which means they can be hacked by external images. This paper just came out yesterday: "Breaking 7/8 of the ICLR 2018 adversarial example defenses" (https://arxiv.org/abs/1802.00420). The situation is dire. I think they are afraid that drawing a couple of lines with a marker on a street sign might make it invisible, or turn it into…

Paper and discussion history. A mention is not an endorsement.

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples · HackerPapers discussions

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples — mentioned by visarga