All Deep Dives For Infosec Conference Talks Covering AI Security. Talks analyzed in full.
![Guardrails beyond Vibes | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-security-agents-production-stripe-guardrails-playbook-jeffrey-zhang-siddh-shah.webp)
Learn how Stripe built and deployed two production AI security agents with multi-agent architecture, LLM-as-judge eval pipelines, and phased rollout.
![Security Guidance as a Service | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/security-guidance-as-a-service-rag-for-appsec-shruti-chandrani.webp)
Learn how Adobe built a RAG-powered security guidance platform delivering org-specific recommendations across Jira, Slack, and IDE at scale.
Learn why precision and recall fail for autonomous AI security agents — and how rubric-based LLM judge evaluation gives your team a reliable deployment bar.
Discover how Google's Big Sleep and Code Mender use agentic AI to find and patch deep memory safety bugs with zero false positives.
Learn a proven 7-phase AI red teaming methodology, prompt injection taxonomy, and real enterprise case studies for assessing LLM systems.
Learn to threat-model AI agents for indirect prompt injection: enumerate tools, map AI-specific attack vectors, and automate dynamic testing with TamperMonkey.
Learn how to build specialized AI security bots and apply generative AI across red team, blue team, and purple team workflows using a proven prompt engineering methodology.
Learn to assess AI code generation security risks—from package hallucination to IP liability—and apply governance controls that protect your SDLC.
Learn to exploit OWASP ML Top 10 risks hands-on — supply chain attacks, data poisoning, and output integrity bypasses against a real AWS SageMaker infrastructure.
Learn how to apply structured threat modeling to AI/ML systems using the ML SecOps framework, three diagnostic questions, and OWASP AI Exchange controls.
Learn how adversarial ML attacks silently bypass AI security controls and how to apply AI security threat modeling using Project Guardrail's tiered questionnaire framework.
