arXiv:2606. 01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2608. 05045v1 Announce Type: cross Abstract: Released aligned large language models remain vulnerable to malicious downstream finetuning.
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.
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 investigates how trigger-based backdoors function in large language models by using sparse autoencoders (SAEs) to identify feature directions across layers and transformer components. In a controlled experiment, 1B and 8B models were made to continue English prompts in French or German when presented with fixed trigger sequences. The study finds that different SAE feature directions correspond to trigger detection, residual-stream propagation, and language tracking, with residual-stream features being most effective for controlling the backdoor behavior.
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.