ToxScreen: Detecting Whether an LLM Has Been Poisoned

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool. We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen. We formalize poison selection as oracle-budgeted set optimization and introduce SAILS (Set-level Audit-Informed Iterative Learned Selection), which learns a set scorer from a few hundred finetune-and-evaluate runs, ranks millions of candidate sets, and audits only a small shortlist. SAILS improves held-out attack success by 30 percentage points on average over the strongest influence baselines, transfers from small-scale to full-scale finetuning, and extends to code-generation, agentic, and API-only backdoors.

Even though backdoors in LLMs have been a growing concern, their inner workings are still under heavy scrutiny. Trigger-based backdoors are easy to define behaviorally, a rare input that makes the model switch to a chosen response pattern, but the mechanism between triggers and their responses is less clear. We study this mechanism in a controlled, harmless language-switching setting, where fixed trigger sequences make 1B and 8B language models continue English prompts in French or German. For this, we train sparse autoencoders (SAEs) across layers and transformer components, then compare triggered prompts with translation and pretraining controls to identify trigger-relevant feature directions. We show how SAE features separate triggered prompts from controls with near-perfect F1, but features that detect the trigger do not necessarily control the behavior. In intervention tests, attention and MLP features often fire reliably on triggered prompts, making them good detectors, but ablating them rarely suppresses the language switch and activating them rarely induces it. In contrast, residual-stream features can suppress triggered generation when ablated, and some selected features can induce target-language continuations without the trigger. In short, these token-trigger mechanisms decompose into distinct SAE feature directions, with separate features for trigger detection, residual-stream propagation, and later language tracking. This role-level decomposition is the part most likely to transfer to other trigger-based backdoors, even when the payload, layers, or circuit locations differ.

Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM rewriting as a proactive defense against data poisoning. First, we theoretically show that when LLM rewriting utilizes open-book benign samples--termed open-book benign rewriting (OBBR)--the probability of a rewritten output being benign is strictly greater than that of closed-book rewriting. Thus, OBBR neutralizes harmful content by projecting training samples to the space of benign prompts. We then show that, in contrast to previous defenses, OBBR effectively mitigates a large number of existing BAs: across five known BAs and four widely used LLMs, OBBR increases safety performance by an average 51% compared to state-of-the-art BA defenses and 25.7% compared to closed-book rewriting methods. Finally, we show that OBBR is computationally efficient relative to other BA defenses, does not degrade model performance on natural language tasks after fine-tuning, and is capable of defending against non-trigger based data poisoning attacks.