March 19, 2024, 4:42 a.m. | Roey Bokobza, Yisroel Mirsky

cs.LG updates on arXiv.org arxiv.org

arXiv:2403.10562v1 Announce Type: cross
Abstract: Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples. Unlike traditional preprocessing defences that rely on sanitizing input samples, our stateless strategy counters the attack process itself. For every query we evaluate a counter-sample instead, where the counter-sample is the original sample optimized against the attacker's objective. By countering every black box query with a targeted white box optimization, our …

abstract adversarial adversarial attacks adversarial examples arxiv attacks black box box craft cs.ai cs.cr cs.lg defence every examples novel oracle paper process query samples stateless strategy type

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

Intern Large Language Models Planning (f/m/x)

@ BMW Group | Munich, DE

Data Engineer Analytics

@ Meta | Menlo Park, CA | Remote, US