Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
Parameter-efficient fine-tuning (PEFT) has become a key training strategy for large language models. However, its reliance on fewer trainable parameters poses security risks, such as task-agnostic backdoors. Despite their severe impact on a wide range of tasks, there is no practical defense solution available that effectively counters task-agnostic backdoors within the context of PEFT. In this study, we introduce Obliviate, a PEFT-integrable backdoor defense. We develop two techniques aimed at amplifying benign neurons within PEFT layers and penalizing the influence of trigger tokens. Our evaluations across three major PEFT architectures show that our method can significantly reduce the attack success rate of the state-of-the-art task-agnostic backdoors (83.6%$\downarrow$). Furthermore, our method exhibits robust defense capabilities against both task-specific backdoors and adaptive attacks. Source code will be obtained at https://github.com/obliviateARR/Obliviate.
Code (0)
등록된 구현이 없습니다.
Tasks
backdoor defenseparameter-efficient fine-tuningSimilar Papers 제목 키워드 기반
Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models
Recent copyright agreements between AI companies and content creators underscore the need for fine-grained control over language models' ability to reproduce copyrighted text. Existing defenses-ranging from aggressive un…
HellaSwagMemorizationMMLUTruthfulQA+1Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
Current backdoor defenses assume that neutralizing a known trigger removes the backdoor. We show this trigger-centric view is incomplete: \emph{alternative triggers}, patterns perceptually distinct from training triggers…
Neutralizing Backdoors through Information Conflicts for Large Language Models
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to back…
backdoor defenseLMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability. Despite its wide adoption, we empirical…
Obliviate: Erasing Concepts from Autoregressive Image Generation Models
The widespread adoption of generative AI models has intensified concerns about misuse, including the creation of unsafe or disturbing imagery. To mitigate such issues, several concept erasure approaches have been propose…
Image Generation