cs.AINov 6, 2026

Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect

Authors: Matt Clarke, Jan Dubiński, James Chua, Simon Schrodi, Owain Evans, Alex Cloud

Organizations: Anthropic Fellows Program; Anthropic · Truthful AI; NASK National Research Institute; Warsaw University of Technology · Anthropic · MATS; University of Freiburg · 

Abstract

We study homeopathic learning, a phenomenon where poisoned training data with little effect on its own can create a hidden backdoor once clean, contrasting data is added. In our experiments, a model fine-tuned only on a "poison" dataset associated with a trait T (such as speaking German or being misaligned) does not learn T. Surprisingly, adding similarly formatted "clean" data not associated with T causes the model to learn T. This effect requires that the poison data have an identifying "trigger" feature that is absent from the clean data. We demonstrate this effect in a variety of settings: subliminal learning of backdoor behaviors, inoculation prompting of reward hacking transcripts, generalization from archaic bird names, and an MNIST classifier with mislabeled data. We propose a simple regression model as an explanation. In the poison data, the task and trigger always co-occur, and regularization favors attributing T to the task. Clean data without the trigger causes T to be attributed to the trigger instead. Consequently, the same training examples can have little effect as part of one training set but create a misalignment backdoor in another. This finding exposes a potential limitation of safety methods that audit or filter training data in isolation.

Figures & tables

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 28, 2026

Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits

Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted generalisation by requesting the undesired behaviour during training and removing the request at inference. However, undesired behaviour can still appear under unrelated prompts. IP can also hinder learning of the desired behaviour. We address these limitations in settings where both behaviours co-occur in most training examples, so filtering out examples with undesired behaviour leaves only a small clean subset. We introduce stratified inoculation prompting (SIP). SIP leverages a small clean subset to demonstrate that desired behaviour should persist without the undesired one across different contexts. SIP oversamples these clean examples under diverse non-eliciting prompts while inoculating the rest. SIP substantially reduces expression of undesired behaviour while preserving more of the desired behaviour than IP. These gains persist even when we extend IP to oversample the same clean subset at the same rate as SIP. Moreover, SIP yields lower emergent misalignment rates in all harmful-advice setups we tested. SIP can be further extended to limit the undesired behaviour even under prompts that explicitly request it. We introduce backdoor dilution, which weakens expression under the inoculation prompt, and password-locked inoculation, which concentrates elicitation on a designated password. Taken together, our findings show that changing the training contexts for a small clean subset can significantly improve selective generalisation.
Jul 7, 2026

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples. In particular, the latter has proven effective for anti-backdoor learning. Our method, HARVEY, leverages a similar yet crucially different technique: learning an oracle for poisonous rather than benign samples. Learning a backdoored reference model is significantly easier than learning a reference model on benign data. Consequently, we can identify poisonous samples much more accurately than related work identifies benign samples. This crucial difference enables near-perfect backdoor removal as we demonstrate in our evaluation. HARVEY substantially outperforms related approaches across attack types, datasets, and architectures, lowering the attack success rate to the very minimum at a negligible loss in natural accuracy. The figure below shows an overview of our methods working principle.
Jul 28, 2026

Lilith: Backdoor Generalization under Training-Inference Trigger Shift

Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persistent malicious behavior while preserving benign utility. However, existing backdoor studies largely evaluate exact trigger reuse, training-exposed trigger diversity, or variations along predefined transformation axes. They therefore leave a critical blind spot: whether a backdoor learned from one training-time trigger can generalize to an inference-time trigger family absent from victim training. We formulate this problem as backdoor generalization under training--inference trigger shift and introduce Lilith, a black-box anchor-to-family framework. Using only disjoint surrogate resources, Lilith first induces a compact target-side vulnerability with a single training anchor, then constructs a bounded inference-only family that preserves the anchor-induced representation geometry. We characterize this mechanism through anchor clearance and family reach, deriving sufficient conditions for family-wise target preservation under local regularity and bounded surrogate--victim discrepancy. Experiments across datasets, architectures, poisoning rates, and defenses show that Lilith achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap. Additional analyses show that family activation depends on representation alignment rather than the proposal mechanism, exposing a broader threat overlooked by exact-trigger evaluation.