Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-28 with 3 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Travis Lelle |
| Year | 2026 |
| HF Upvotes | 3 |
| arXiv | 2605.30189 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
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.
Engineering Breakdown
The Problem
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.
The Approach
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.
Key Results
Behavioral detection is the operationally portable result for adapter supply chain scanning.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Tokenlevel
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::