March 19, 2024, 4:11 a.m. | Shijie Liu, Andrew C. Cullen, Paul Montague, Sarah M. Erfani, Benjamin I. P. Rubinstein

cs.CR updates on arXiv.org arxiv.org

arXiv:2308.07553v2 Announce Type: replace-cross
Abstract: Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them potentially countered by novel attacks. In contrast, by examining worst-case behaviours Certified Defences make it possible to provide guarantees of the robustness of a sample against adversarial attacks modifying a finite number of training samples, known as pointwise certification. We achieve this …

arxiv attacks can case certifications certified cs.cr cs.lg general influence making novel poisoning poisoning attacks training

Security Analyst

@ Northwestern Memorial Healthcare | Chicago, IL, United States

GRC Analyst

@ Richemont | Shelton, CT, US

Security Specialist

@ Peraton | Government Site, MD, United States

Information Assurance Security Specialist (IASS)

@ OBXtek Inc. | United States

Cyber Security Technology Analyst

@ Airbus | Bengaluru (Airbus)

Vice President, Cyber Operations Engineer

@ BlackRock | LO9-London - Drapers Gardens