Nov. 17, 2022, 2:20 a.m. | Mengxin Zheng, Qian Lou, Lei Jiang

cs.CR updates on arXiv.org arxiv.org

Vision Transformers (ViTs) have demonstrated the state-of-the-art performance
in various vision-related tasks. The success of ViTs motivates adversaries to
perform backdoor attacks on ViTs. Although the vulnerability of traditional
CNNs to backdoor attacks is well-known, backdoor attacks on ViTs are
seldom-studied. Compared to CNNs capturing pixel-wise local features by
convolutions, ViTs extract global context information through patches and
attentions. Na\"ively transplanting CNN-specific backdoor attacks to ViTs
yields only a low clean data accuracy and a low attack success rate. In …

transformers trojan

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

Cryptography Software Developer

@ Intel | USA - AZ - Chandler

Lead Consultant, Geology

@ WSP | Richmond, VA, United States

BISO Cybersecurity Director

@ ABM Industries | Alpharetta, GA, United States