cs.CRNov 2, 2026

LoRA-Patch: Defending Against Backdoored LoRA Adapters via Directional Steering

Authors: Shengyan Huo, Peihai Jiang, Xixiang Lyu, Yige Li

Organizations: Xidian University, China · Singapore Management University, Singapore

Abstract

Third-party LoRA adapters introduce serious backdoor risks: malicious adapters can maintain normal task performance while embedding hidden, trigger-activated behaviors, making them difficult to detect through standard utility evaluations. Existing removal-based defenses typically sanitize backdoored models by updating, pruning, distilling, or mixing model parameters. However, these approaches are misaligned with adapter-based deployment, where the trusted base model is expected to remain frozen. In this work, we propose LoRA-Patch, a lightweight backdoor defense tailored to LoRA adapters. Our key insight is that backdoor injection distorts the directional geometry of a poisoned adapter relative to its trusted base model. Building on this insight, LoRA-Patch suppresses trigger-activated behaviors by realigning adapter directions through layer-wise steering, without modifying the base model weights. Extensive experiments across five backdoor attacks and three models show that LoRA-Patch effectively mitigates trigger-activated backdoors, outperforming existing baselines while preserving benign task performance. Moreover, LoRA-Patch is computationally efficient, constructing patches within 20 seconds across all evaluated models and adapters. Our code is publicly available at https://github.com/FOXVEDA/LoRA-Patch.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Weight space Detection of Backdoors in LoRA Adapters

    Feb 16, 2026David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu +2Backdoor DetectionBackdoor Defense in LLMs

  2. LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

    Aug 7, 2026Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1LLM Backdoor AttacksBackdoor Detection