BadMerging: Backdoor Attacks Against Model Merging

v1v2 (latest)

BadMerging: Backdoor Attacks Against Model Merging

14 August 2024

Zheng Li

Yang Zhang

Yuan Tian

ArXiv (abs)PDF HTML

Papers citing "BadMerging: Backdoor Attacks Against Model Merging"

5 / 5 papers shown

Title
Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging Lin Lu Zhigang Zuo Ziji Sheng Pan Zhou MoMe 131 0 0 22 Feb 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 123 0 0 17 Feb 2025
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning Zhen Sun Tianshuo Cong Yule Liu Chenhao Lin Xinlei He Rongmao Chen Xingshuo Han Xinyi Huang AAML 172 6 0 26 Nov 2024
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace Jinluan Yang Anke Tang Didi Zhu Zhengyu Chen Li Shen Leilei Gan MoMe AAML 164 7 0 17 Oct 2024
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning Yun Luo Zhen Yang Fandong Meng Yafu Li Jie Zhou Yue Zhang CLL KELM 201 319 0 17 Aug 2023