Similar Items: Jailbroken Frontier Models Retain Their Capabilities
- Assessing Generalisation Capability of Machine Learning Models for Intrusion Detection
- Cross-Modal Backdoors in Multimodal Large Language Models
- VOW: Verifiable and Oblivious Watermark Detection for Large Language Models
- Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery
- Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
- SoK: Robustness in Large Language Models against Jailbreak Attacks