Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

17 October 2024

Papers citing "Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace"

3 / 3 papers shown

Title
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets W. Liu Zhongyu Niu Lang Gao Zhiying Deng Jun Wang H. Wang Ruixuan Li 41 1 0 04 May 2025
Defending Deep Neural Networks against Backdoor Attacks via Module Switching Weijun Li Ansh Arora Xuanli He Mark Dras Qiongkai Xu AAML MoMe 42 0 0 08 Apr 2025
Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy Zhenyuan Guo Yi Shi Wenlong Meng Chen Gong Chengkun Wei Wenzhi Chen MoMe 55 0 0 17 Feb 2025