# technique
標記為「technique」的 24 篇文章
Attack Technique Index
Comprehensive index of attack techniques organized by target, difficulty, and defense-bypass approach.
API Parameter Exploitation Walkthrough
Walkthrough of exploiting undocumented and misconfigured API parameters in LLM service endpoints.
Batch API Exploitation Walkthrough
Walkthrough of exploiting batch processing APIs for large-scale prompt injection and output analysis.
Cognitive Overload Jailbreak Walkthrough
Step-by-step walkthrough of the cognitive overload technique that overwhelms safety training with complex nested instructions.
Context Virtualization Attack Walkthrough
Walkthrough of creating virtualized contexts that make the model believe it is operating in a different environment.
Conversation Poisoning Attack Walkthrough
Step-by-step walkthrough of poisoning conversation history to alter model behavior in future turns.
Instruction Hierarchy Exploitation Walkthrough
Walkthrough of exploiting how models prioritize system, user, and tool instructions to override safety directives.
Multi-Provider Attack Campaign Walkthrough
End-to-end walkthrough of conducting an attack campaign across OpenAI, Anthropic, Google, and open-source models.
Output Format Exfiltration Techniques Walkthrough
Walkthrough of using output format manipulation to exfiltrate data through code blocks, markdown, and structured outputs.
Refusal Suppression Technique Walkthrough
Walkthrough of refusal suppression techniques that prime models to avoid safety refusal patterns.
Semantic Obfuscation Walkthrough
Walkthrough of semantically obfuscating adversarial payloads so they appear benign to both classifiers and humans.
Structured Output Data Leakage Walkthrough
Walkthrough of using structured output requirements to extract sensitive data embedded in model responses.
攻擊 Technique Index
Comprehensive index of attack techniques organized by target, difficulty, and defense-bypass approach.
API Parameter 利用ation 導覽
導覽 of exploiting undocumented and misconfigured API parameters in LLM service endpoints.
Batch API 利用ation 導覽
導覽 of exploiting batch processing APIs for large-scale prompt injection and output analysis.
Cognitive Overload 越獄 導覽
Step-by-step walkthrough of the cognitive overload technique that overwhelms safety training with complex nested instructions.
Context Virtualization 攻擊 導覽
導覽 of creating virtualized contexts that make the model believe it is operating in a different environment.
Conversation 投毒 攻擊 導覽
Step-by-step walkthrough of poisoning conversation history to alter model behavior in future turns.
Instruction Hierarchy 利用ation 導覽
導覽 of exploiting how models prioritize system, user, and tool instructions to override safety directives.
Multi-Provider 攻擊 Campaign 導覽
End-to-end walkthrough of conducting an attack campaign across OpenAI, Anthropic, Google, and open-source models.
Output Format Exfiltration Techniques 導覽
導覽 of using output format manipulation to exfiltrate data through code blocks, markdown, and structured outputs.
Refusal Suppression Technique 導覽
導覽 of refusal suppression techniques that prime models to avoid safety refusal patterns.
Semantic Obfuscation 導覽
導覽 of semantically obfuscating adversarial payloads so they appear benign to both classifiers and humans.
Structured Output Data Leakage 導覽
導覽 of using structured output requirements to extract sensitive data embedded in model responses.