Similar Items: Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
- PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
- SoK: Robustness in Large Language Models against Jailbreak Attacks
- ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
- TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
- SCRIBE: Practical Static Binary Patching via Binary-Aware Recompilation of Decompiled Code
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization