llm-security 6
- Automating AI Hacking with Tree of Attack
- Your AI agent doesn't know your codebase's context or constraints, and that's costing you
- Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety
- Putting models to the secure coding test: Plan vs default mode
- Race Against The Patch: The Evolution of Four Exploit Chains in LiteLLM
- Securing AI agents: Why guardrail placement is a key design decision