all AI news
Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre
May 7, 2024, 4:44 a.m. | Nicholas Carlini
cs.LG updates on arXiv.org arxiv.org
Abstract: Sabre is a defense to adversarial examples that was accepted at IEEE S&P 2024. We first reveal significant flaws in the evaluation that point to clear signs of gradient masking. We then show the cause of this gradient masking: a bug in the original evaluation code. By fixing a single line of code in the original repository, we reduce Sabre's robust accuracy to 0%. In response to this, the authors modify the defense and introduce …
abstract adversarial adversarial examples arxiv clear code cs.cr cs.lg defense evaluation example examples flaws gradient ieee line masking show through type
More from arxiv.org / cs.LG updates on arXiv.org
Efficient Data-Driven MPC for Demand Response of Commercial Buildings
2 days, 22 hours ago |
arxiv.org
Testing the Segment Anything Model on radiology data
2 days, 22 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 22 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US