cs.CRAug 3, 2025

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models

Authors: Man Hu, Yahui Ding, Yatao Yang, Liangyu Chen, Yanhao Jia, Shuai Zhao

Organizations: Beijing Electronic Science and Technology Institute, China · Nanyang Technological University, Singapore

Abstract

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full retraining or additional clean models. To address these challenges, we propose DUP (Detection-guided Unlearning for Purification), a unified framework that integrates backdoor detection with unlearning-based purification. The detector captures feature-level anomalies by jointly leveraging class-agnostic distances and inter-layer transitions. These deviations are integrated through a weighted scheme to identify poisoned inputs, enabling more fine-grained analysis. Based on the detection results, we purify the model through a parameter-efficient unlearning mechanism that avoids full retraining and does not require any external clean model. Specifically, we innovatively repurpose knowledge distillation to guide the student model toward increasing its output divergence from the teacher on detected poisoned samples, effectively forcing it to unlearn the backdoor behavior. Extensive experiments across diverse attack methods and language model architectures demonstrate that DUP achieves superior defense performance in detection accuracy and purification efficacy. Our code is available at https://github.com/ManHu2025/DUP.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Feb 24, 2026

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that well-established data-poisoning pipelines can successfully implant backdoors into MDLMs, enabling attackers to manipulate model behavior via specific triggers while maintaining normal performance on clean inputs. However, defense strategies effective to these models are yet to emerge. To bridge this gap, we introduce a backdoor defense framework for MDLMs named DiSP (Diffusion Self-Purification). DiSP is driven by a key observation: selectively masking certain vision tokens at inference time can neutralize a backdoored model's trigger-induced behaviors and restore normal functionality. Building on this, we purify the poisoned dataset using the compromised model itself, then fine-tune the model on the purified data to recover it to a clean one. Given such a specific design, DiSP can remove backdoors without requiring any auxiliary models or clean reference data. Extensive experiments demonstrate that our approach effectively mitigates backdoor effects, reducing the attack success rate (ASR) from over 90% to typically under 5%, while maintaining model performance on benign tasks.
Jun 2, 2026

Patcher: Post-Hoc Patching of Backdoored Large Language Models

Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical when defenders only observe a single reported failure case without knowing whether it stems from a backdoor attack or a natural alignment bug. This paper presents Patcher, a post-hoc defense framework that repairs backdoored language models using only a single reported failure case and the model parameters. Patcher operates in two stages. First, it localizes backdoor triggers by computing response-conditioned gradient-based saliency scores and applying adaptive clustering to separate triggers from benign context. Second, it patches the model through a constrained fine-tuning objective that breaks the trigger-response association while preserving benign-task utility and robustness to non-triggered jailbreak attacks through KL-divergence constraints. We conduct extensive evaluations across multiple backdoor attack strategies and demonstrate that Patcher successfully localizes triggers and neutralizes backdoors while maintaining model utility. We further show robustness against adaptive attacks designed to evade our defense. This work represents a significant step toward practical defenses against training-time attacks in deployed language models.
Mar 13, 2026

Test-Time Attention Purification for Backdoored Large Vision Language Models

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be maliciously activated at test time. Existing defenses typically rely on retraining backdoored parameters (e.g., adapters or LoRA modules) with clean data, which is computationally expensive and often degrades model performance. In this work, we provide a new mechanistic understanding of backdoor behaviors in LVLMs: the trigger does not influence prediction through low-level visual patterns, but through abnormal cross-modal attention redistribution, where trigger-bearing visual tokens steal attention away from the textual context - a phenomenon we term attention stealing. Motivated by this, we propose CleanSight, a training-free, plug-and-play defense that operates purely at test time. CleanSight (i) detects poisoned inputs based on the relative visual-text attention ratio in selected cross-modal fusion layers, and (ii) purifies the input by selectively pruning the suspicious high-attention visual tokens to neutralize the backdoor activation. Extensive experiments show that CleanSight significantly outperforms existing pixel-based purification defenses across diverse datasets and backdoor attack types, while preserving the model's utility on both clean and poisoned samples.