all AI news
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
Feb. 22, 2024, 5:41 a.m. | Zhiwei Wang, Huazheng Wang, Hongning Wang
cs.LG updates on arXiv.org arxiv.org
Abstract: Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily detected by our proposed detection method based on the test of homogeneity, due to their aggressive nature in reward manipulations. This motivates us to study the notion of stealthy attack against stochastic MABs and investigate the resulting attackability. Our analysis shows that against …
abstract adversarial adversarial attacks algorithms arxiv attacks cs.cr cs.lg detection focus literature multi-armed bandits poisoning attacks stochastic test type work
More from arxiv.org / cs.LG updates on arXiv.org
Testing the Segment Anything Model on radiology data
1 day, 18 hours ago |
arxiv.org
Calorimeter shower superresolution
1 day, 18 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