# technique
12 artikelengetagd met “technique”
Index van aanvalstechnieken
Uitgebreide index van aanvalstechnieken, georganiseerd op doel, moeilijkheidsgraad en aanpak om verdediging te omzeilen.
Walkthrough: misbruik van API-parameters
Walkthrough of exploiting undocumented and misconfigured API parameters in LLM service endpoints.
Walkthrough: misbruik van de Batch API
Walkthrough of exploiting batch processing APIs for large-scale prompt injection and output analysis.
Walkthrough: jailbreak via cognitieve overbelasting
Step-by-step walkthrough of the cognitive overload technique that overwhelms safety training with complex nested instructions.
Walkthrough: context virtualization-aanval
Walkthrough of creating virtualized contexts that make the model believe it is operating in a different environment.
Walkthrough: conversation poisoning-aanval
Step-by-step walkthrough of poisoning conversation history to alter model behavior in future turns.
Walkthrough: misbruik van de instructiehiërarchie
Walkthrough of exploiting how models prioritize system, user, and tool instructions to override safety directives.
Walkthrough van een multi-provider-aanvalscampagne
End-to-end walkthrough of conducting an attack campaign across OpenAI, Anthropic, Google, and open-source models.
Walkthrough van exfiltratietechnieken via het uitvoerformaat
Walkthrough of using output format manipulation to exfiltrate data through code blocks, markdown, and structured outputs.
Walkthrough van de techniek voor weigeringsonderdrukking
Walkthrough of refusal suppression techniques that prime models to avoid safety refusal patterns.
Walkthrough van semantische obfuscatie
Walkthrough of semantically obfuscating adversarial payloads so they appear benign to both classifiers and humans.
Walkthrough van datalekkage via gestructureerde uitvoer
Walkthrough of using structured output requirements to extract sensitive data embedded in model responses.