KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

Documenti analoghi

• JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
  di: Li, Hongyi, et al.
  Pubblicazione: (2024)
• Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
  di: Yang, Xiao, et al.
  Pubblicazione: (2024)
• RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
  di: Chen, Xuan, et al.
  Pubblicazione: (2024)
• Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
  di: Wang, Wenqiang, et al.
  Pubblicazione: (2025)
• AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
  di: Li, Yanjie, et al.
  Pubblicazione: (2025)