Exploring the Orthogonality and Linearity of Backdoor Attacks
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Guanhong Tao, Shengwei An, Anuran Makur
IEEE Symposium on Security and Privacy 2024 · Day 2 · Continental Ballroom 5
In this insightful talk from IEEE S&P, Kaiyuan Zhang, a PhD student from Purdue University, presented a systematic study titled "Exploring the Orthogonality and Linearity of Backdoor Attacks." The research, a joint effort between Purdue and NVIDIA, delves into the fundamental reasons why existing defenses often fail against sophisticated backdoor attacks in machine learning models. With the increasing power and prevalence of AI, including large language models (LLMs) and diffusion models, their vulnerability to backdoor attacks has become a critical concern across both academia and industry.
AI review
This talk provides a foundational theoretical framework for understanding backdoor attacks through the concepts of orthogonality and linearity. By formalizing why backdoors persist and introducing actionable metrics, it offers crucial insights for developing more robust and predictable AI defenses, moving beyond empirical trial-and-error.