← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-long.1113 · 记录 #1
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:56
摘要
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale datasets—often collected from human or web sources—makes them vulnerable to backdoor attacks, where adversaries poison a small subset of data to implant hidden behaviors. Despite this growing risk, defenses for instruction-tuned models remain underexplored. We propose MB-Defense (Merging & Breaking Defense Framework), a novel training pipeline that immunizes instruction-tuned LLMs against diverse backdoor threats. MB-Defense comprises two stages: (i) Defensive Poisoning, which merges attacker and defensive triggers into a unified backdoor representation, and (ii) Backdoor Neutralization, which breaks this representation through additional training to restore clean behavior. Extensive experiments across multiple LLMs show that MB-Defense substantially lowers attack success rates while preserving instruction-following ability. Our method offers a generalizable and data-efficient defense strategy, improving the robustness of instruction-tuned LLMs against unseen backdoor attacks.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale datasets—often collected from human or web sources—makes them vulnerable to backdoor attacks, where adversaries poison a small subset of data to implant hidden behaviors. Despite this growing risk, defenses for instruction-tuned models remain underexplored. We propose MB-Defense (Merging & Breaking Defense Framework), a novel training pipeline that immunizes instruction-tuned LLMs against diverse backdoor threats. MB-Defense comprises two stages: (i) Defensive Poisoning, which merges attacker and defensive triggers into a unified backdoor representation, and (ii) Backdoor Neutralization, which breaks this representation through additional training to restore clean behavior. Extensive experiments across multiple LLMs show that MB-Defense substantially lowers attack success rates while preserving instruction-following ability. Our method offers a generalizable and data-efficient defense strategy, improving the robustness of instruction-tuned LLMs against unseen backdoor attacks.
查看此版本解读 →查看此版本原文 ↗