Similar Items: Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
- MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
- On the Privacy of LLMs: An Ablation Study
- Attention Is Where You Attack
- Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
- GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training
- Trident: Improving Malware Detection with LLMs and Behavioral Features