all AI news
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Feb. 26, 2024, 5:42 a.m. | Yihao Zhang, Hangzhou He, Jingyu Zhu, Huanran Chen, Yifei Wang, Zeming Wei
cs.LG updates on arXiv.org arxiv.org
Abstract: Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from a fundamental tradeoff that inevitably decreases clean accuracy. Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization. However, as SAM is designed for better clean accuracy, its effectiveness in enhancing adversarial robustness remains …
adversarial adversarial training arxiv cs.ai cs.cr cs.lg math.oc training type
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
2 days, 9 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
2 days, 9 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
2 days, 9 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
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
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York