Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kim, San, Lee, Gary Geunbae
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917421808353280
author Kim, San
Lee, Gary Geunbae
author_facet Kim, San
Lee, Gary Geunbae
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04448
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
Kim, San
Lee, Gary Geunbae
Computation and Language
Artificial Intelligence
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.
title Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.04448