Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models

Linzhi Chen, Yang Sun, Hongru Wei, Yuqi Chen. Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models. In 33rd Annual Network and Distributed System Security Symposium, NDSS 2026, San Diego, California, USA, February 23-27, 2026. The Internet Society, 2026. [doi]

Authors

Linzhi Chen

This author has not been identified. Look up 'Linzhi Chen' in Google

Yang Sun

This author has not been identified. Look up 'Yang Sun' in Google

Hongru Wei

This author has not been identified. Look up 'Hongru Wei' in Google

Yuqi Chen

This author has not been identified. Look up 'Yuqi Chen' in Google