arXiv AI
Hidden State Poisoning Attacks against Mamba-based Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 30
Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...
arXiv AI
Oct 15
What the Model Cannot See: Covert and Provable Text Invisibility in LLMs
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answerin...
arXiv AI
Jul 20
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.
arXiv AI
Jul 23
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv Machine Learning
Oct 2
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
The paper introduces SparLeak, a side‑channel attack that exploits a new GPU micro‑architectural leakage called Sparsity‑Induced Memory Access (SIMA) caused by sparse attention in large language models. By capturing SIMA traces during LLM inference, SparLeak can infer user‑query attributes from prefill‑phase traces and reconstruct autoregressive responses from decoding‑phase traces. Experiments on three LLM architectures, three sparse attention mechanisms, and three privacy‑sensitive datasets show high success rates (90.9% for attribute inference and 87.3% for response reconstruction), underscoring the need to address SIMA leakage in sparse‑attention deployments.
arXiv AI
Jun 30
Mechanistically Eliciting Latent Behaviors in Language Models
arXiv:2606. 29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes.