SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack

ArXi:2605.24958v1 Announce Type: cross Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that generate adversarial examples using surrogate models without accessing the victim model. Transferable attacks in the text domain are still under-explored, with only a few studies addressing this challenging issue, often with suboptimal results due to equal treatment of submodels or inaccurate estimation of importance scores.