The paper introduces NEEDLE, a training‑free technique for removing backdoors from large language models. After a trigger is identified, NEEDLE estimates a backdoor direction and a refusal subspace using activation vectors, then applies sequential weight orthogonalisation to suppress the backdoor while preserving refusal‑related representations. The method requires no clean reference model or original poisoned data and achieves the lowest attack success rate and minimal impact on model performance across multiple model families and attack types.
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.
The paper introduces a method to purify LoRA-tuned large language models (LLMs) against backdoor attacks without relying on trigger knowledge, clean references, or retraining. By extracting high‑fidelity backdoor directions and projecting LoRA updates onto orthogonal null spaces in input and output channels, the approach reduces attack success rates from nearly 100% to under 10%. Experiments demonstrate that this null‑space projection preserves both the base model’s general capabilities and the new downstream skills learned through the adapter across various tasks.
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
The paper introduces Quarantined Expert Shutdown (QES), a new backdoor containment strategy for large language models. QES allows backdoor learning to occur during training but routes it into a designated, quarantined expert that can be disabled at deployment. The method achieves significant reductions in attack success rates while largely preserving model utility.
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv:2607. 05748v1 Announce Type: new Abstract: The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning.
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...
arXiv:2608. 00732v1 Announce Type: new Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
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.
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.