Topic
All digests tagged LLM Vulnerabilities
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
The workshop details the shift from traditional software security to AI-native defenses, covering topics like Prompt Injection, AI Bomb inventory, and integrating security hooks into CI/CD pipelines for agentic workflows.
Read article
The discussion explores Prompt Injection as Role Confusion, detailing how attackers forge chain-of-thought reasoning to bypass LLM guardrails. Key mitigation strategies include implementing instruction hierarchies and sandboxing.
Read article