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

Feb 16, 2026

Weight space Detection of Backdoors in LoRA Adapters

LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current detection methods require running the model with test input data -- making them impractical for screening thousands of adapters where the trigger for backdoor behavior is unknown. We detect poisoned adapters by analyzing their weight matrices directly, without running the model -- making our method trigger-agnostic. For each attention projection (Q, K, V, O), our method extracts five spectral statistics from the low-rank update ΔWΔW, yielding a 20-dimensional signature for each adapter. A logistic regression detector trained on this representation separates benign and poisoned adapters across three model families -- Llama-3.2-3B~\citep{llama3}, Qwen2.5-3B~\citep{qwen25}, and Gemma-2-2B~\citep{gemma2} -- on unseen test adapters drawn from instruction-following, reasoning, question-answering, code, and classification tasks. Across all three architectures, the detector achieves 100% accuracy.
Aug 7, 2026

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

Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes backdoor signals and reduces detection performance. Existing adapter-aware methods do not address how to safely use a potentially backdoored adapter. Instead, they either train a defensive adapter to repair a backdoored base model, addressing the inverse problem rather than securing the adapter itself, or rely on a classifier that flags the entire adapter as suspicious and requires separate mitigation. These methods overlook the distinct latent-space signatures produced by trigger-bearing inputs in backdoored adapters. We introduce LoRAScan, the first adapter-aware defense that detects and rejects trigger-bearing inputs at inference time without modifying adapter parameters. Our key observation is that a small subset of LoRA insertion sites, approximately 5%, remains stable across clean inputs but exhibits highly concentrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance insertion sites before model deployment and monitors them during inference. Across standard LLM backdoor benchmarks, LoRAScan rejects 98.49% of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings.
May 28, 2026

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while preserving baseline task performance. On a Qwen 2.5 1.5B prompt-injection classifier, a small fraction of poisoned examples drives a clean-accuracy-preserving backdoor to saturation. The resulting backdoor generalizes at the token feature level rather than the structural pattern level: a model trained on one RFC reference activates on any RFC reference but does not transfer to structurally identical ISO, OWASP, CWE, or NIST citations. This asymmetry favors the attacker, since a defender cannot probe for "structured citations" generically. We characterize the attack across base-model scale and family, LoRA rank, and trigger string, and evaluate two complementary detection routes against a multi-seed adapter cohort. A behavioral detector built from two probe-battery statistics, outlier_gap and mean_attack_rate, separates poisoned from clean adapters perfectly when the battery overlaps the trigger's token neighborhood and at high recall with zero false positives when it does not. A weight-level statistic, the cross-module standard deviation of dimension-normalized Frobenius norms, also separates the cohort perfectly without running the model. Combined, the two routes are robust to probe composition. Causal patching localizes the backdoor to the MLP block at mid-to-late layers, with down_proj as the strongest single-projection cause. Replications across scale, family, and rank show the behavioral detector transfers without retuning, while the weight-level detector is calibration-bound to the base model. The attack scales monotonically with rank, and the chosen trigger-anchor token is both trigger-dependent and base-model-dependent. Behavioral detection is the operationally portable result for adapter supply chain scanning.