v1v2 (latest)

The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples

6 May 2023

Papers citing "The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples"

2 / 2 papers shown

Title
Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack Daewon Kang YeongHwan Shin Doyeon Kim Kyu-Hwan Jung Meong Hi Son AAML SILM 40 0 0 17 Jun 2025
Generating Natural Adversarial Examples Zhengli Zhao Dheeru Dua Sameer Singh GAN AAML 194 601 0 31 Oct 2017