all AI news
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
March 22, 2024, 4:44 a.m. | Pascal Zimmer, S\'ebastien Andreina, Giorgia Azzurra Marson, Ghassan Karame
cs.LG updates on arXiv.org arxiv.org
Abstract: Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only …
abstract accuracy arxiv attacks cs.cr cs.cv cs.lg gap price query robustness samples show solid test type work
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Machine Learning Engineer
@ Samsara | Canada - Remote