Unverified50% confidenceFactExact time
Common forms of prompt injection attacks include direct injection, indirect injection, and jailbreak attacks.
1
Sources
50%
Confidence
Long-term
Relevance
9/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThrough carefully crafted jailbreak prompts, attackers can bypass the safety guardrails of mainstream LLMs to generate harmful content.77% similarUnverifiedjailbreak攻击（如DAN提示、Base64编码指令、多语言切换攻击）本质上是试图将模型推入训练分布之外，使其进入对齐约束薄弱的行为空间71% similarVerifiedPrompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束69% similarUnverifiedA backdoor attack refers to an attack in which the adversary plants a trigger in the training data so that the model behaves normally on clean inputs but produces a preset malicious output when it encounters a specific trigger.68% similarUnverified攻击面通常分为三类：网络攻击面、软件攻击面和人员攻击面67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/875628API
curl https://kongchang.com/api/v1/knowledge/claims/875628MCP
get_claim(id=875628)