Document Type

Article

Publication Date

8-7-2026

Department

Department of Electrical and Computer Engineering

Abstract

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 gen- erate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trig- ger. 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 se- curing 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 con- centrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance in- sertion sites before model deployment and monitors them dur- ing inference. Across standard LLM backdoor benchmarks, LoRAScan rejects approximately 98.49% of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings.

Version

Preprint

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.