Defense Against Syntactic Textual Backdoor Attacks with Token Substitution
원문 초록
Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same triggers as a certain class. Prior backdoor defense methods primarily target special token-based triggers, leaving syntax-based triggers insufficiently addressed. To fill this gap, this paper proposes a novel online defense algorithm that effectively counters syntax-based as well as special token-based backdoor attacks. The algorithm replaces semantically meaningful words in sentences with entirely different ones but preserves the syntactic templates or special tokens, and then compares the predicted labels before and after the substitution to determine whether a sentence contains triggers. Experimental results confirm the algorithm's performance against these two types of triggers, offering a comprehensive defense strategy for model integrity.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
Mitigating Object Hallucinations via Sentence-Level Early Intervention
AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles
Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
토론
이 논문과 연결된 포럼 글이 아직 없습니다.