Similar Items: TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
- SoK: Robustness in Large Language Models against Jailbreak Attacks
- ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
- Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
- Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI Package Ecosystems
- Noisy Networks, Nosy Neighbors: Simple Privacy Attacks Against Residential Wireless Traffic
- On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference