Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing

Documenti analoghi

• Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
  di: Yan, Yu, et al.
  Pubblicazione: (2026)
• BotSim: LLM-Powered Malicious Social Botnet Simulation
  di: Qiao, Boyu, et al.
  Pubblicazione: (2024)
• Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
  di: Ouyang, Sheng, et al.
  Pubblicazione: (2025)
• Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars
  di: Yan, Yu, et al.
  Pubblicazione: (2024)
• Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
  di: Zhang, Yunyi, et al.
  Pubblicazione: (2025)