Unverified50% confidenceFactExact time
LLM jailbreaking refers to an attacker using carefully crafted prompts to induce a model to break through its built-in safety alignment or system instructions and perform actions that should be prohibited.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM-as-Attacker范式用一个专门微调的攻击LLM持续生成对抗提示，再由裁判LLM评估目标模型响应是否违规，形成无需人工介入的闭环79% similarUnverified基于LLM的系统天然面临提示词注入（Prompt Injection）攻击75% similarUnverifiedLLM Agent behavior is gradually generated by the model at runtime based on context, the risk of the same permission differs drastically across different contexts, and the combinatorial behavior space far exceeds any static enumeration capability.75% similarUnverifiedIndirect prompt injection is harder to defend against than direct injection because the attack payload is hidden within external content the model is supposed to trust, exploiting the fundamental characteristic of LLMs that mixes instructions with data.74% similarUnverifiedThe ability to make a model 'ignore all previous instructions' shares the same origin as the prompt injection problem in the security field; attackers exploit the model's tendency to obey instructions that appear later by embedding malicious instructions in web page content or documents to hijack the model's behavior.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016206API
curl https://kongchang.com/api/v1/knowledge/claims/1016206MCP
get_claim(id=1016206)