Diagnosing Poisoning Effects in Adapted LLM Guardrails: Beyond Fixed-Threshold Evaluation
Desk rejected at ICLR 2027, so left out of the paper lists and the map.
Abstract
LLM guardrails are increasingly adapted with newly collected feedback, but evaluating an updated guard at its old deployment threshold mixes two effects: ordinary adaptation can move the operating point, while poisoned feedback can additionally degrade ranking. We ask how to distinguish poisoning-induced degradation from adaptation-induced operating-point drift. We first conduct controlled INJECTION→SAFE label-flip experiments on encoder guardrails. DistilBERT-CE and DeBERTa-GCE, three training seeds, and 1–10% corruption reveal dose-dependent behavior whose magnitude and ranking effects vary by architecture, seed, and evaluation distribution. Frozen-threshold blocking can change dramatically even when threshold-independent ranking changes little. A locked DeBERTa evaluation and a BIPIA-derived external evaluation further show that restoring a measured operating point on one distribution does not establish transfer to another. We then study an online 4-bit QLoRA guard with clean and 10%-poisoned updates, a frozen Mistral downstream model, HarmBench, and XSTest. Both clean and poisoned adaptation move fixed-threshold operating points toward severe over-refusal, so the fixed threshold alone does not isolate poisoning. Prompt-level CPU-only reanalysis separates these mechanisms. Under the all-HarmBench ranking definition, clean-adapted AUROC ranges from 0.82 to 0.98, whereas poisoned-adapted AUROC ranges from 0.09 to 0.48; the Judge-positive analysis likewise yields paired poisoning losses in all three seeds. At the exact shared BR≈20% point available for seed 29, Clean HR is 28.02% and Poisoned HR is 52.59%, a +24.57 percentage-point gap (95% CI 18.97–30.17). Broader empirical budget frontiers are worse in 11 of 12 estimable seed–budget cells. These results motivate reporting fixed and adjusted operating points together with ranking and matched-utility analyses, rather than treating a fixed threshold as a poisoning-specific measure.