Web: http://arxiv.org/abs/2112.03477

Jan. 10, 2022, 2:20 a.m. | Behnam Ghavami, Mani Sadati, Mohammad Shahidzadeh, Zhenman Fang, Lesley Shannon

cs.CR updates on arXiv.org arxiv.org

Adversarial bit-flip attack (BFA) on Neural Network weights can result in
catastrophic accuracy degradation by flipping a very small number of bits. A
major drawback of prior bit flip attack techniques is their reliance on test
data. This is frequently not possible for applications that contain sensitive
or proprietary data. In this paper, we propose Blind Data Adversarial Bit-flip
Attack (BDFA), a novel technique to enable BFA without any access to the
training or testing data. This is achieved by …

attack data networks

More from arxiv.org / cs.CR updates on arXiv.org

Staff Reverse Engineer

@ Dragos, Inc. | Remote - USA

Cybersecurity Engineer

@ Sigma Defense | San Diego, California, United States

Sr Staff Engineer/Principal Engineer(Security Researcher, Security Efficacy)

@ Netskope | Bengaluru, Karnataka, India

Information Security Manager - Zurich, CH

@ Scandit | Zurich

Senior Developer C/Go (Acronis Cyber Infrastructure)

@ Acronis | Belgrade, Stari Grad, Serbia

Intermediate Security Analyst

@ ATB Financial | Calgary, Alberta, Canada