類似資料

• Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
  著者:: Yin, Ziyi, 等
  出版事項: (2025)
• VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
  著者:: Yin, Ziyi, 等
  出版事項: (2024)
• Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
  著者:: Li, Changjiang, 等
  出版事項: (2024)
• Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
  著者:: Liu, Xiaoqun, 等
  出版事項: (2024)
• Robustifying Safety-Aligned Large Language Models through Clean Data Curation
  著者:: Liu, Xiaoqun, 等
  出版事項: (2024)