Skip to content
conftrace_

backdoor attack mitigation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

inference-time defense (1) large language model (1) attack success rate (1) decoding strategy (1) backdoor attack (1) text generation (1) adversarial learning (1)

Papers

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models EMNLP 2024