Towards Unified Robustness Against Both Backdoor and Adversarial Attacks

28 May 2024

Papers citing "Towards Unified Robustness Against Both Backdoor and Adversarial Attacks"

6 / 6 papers shown

Title
REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models Chongye Guo Jinhu Fu Junfeng Fang Kun Wang Guorui Feng 34 0 0 20 Apr 2025
How Secure is Forgetting? Linking Machine Unlearning to Machine Learning Attacks M. Prabhakaran S. Nicolazzo Antonino Nocera Vinod Puthuvath AAML MU 91 0 0 26 Mar 2025
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features Mingli Zhu Shaokui Wei Hongyuan Zha Baoyuan Wu AAML 37 0 0 23 Feb 2025
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace Jinluan Yang A. Tang Didi Zhu Zhengyu Chen Li Shen Fei Wu MoMe AAML 52 3 0 17 Oct 2024
Adversarial Backdoor Defense in CLIP Junhao Kuang Siyuan Liang Jiawei Liang Kuanrong Liu Xiaochun Cao AAML 34 2 0 24 Sep 2024
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 250 5,830 0 08 Jul 2016