All Deep Dives For Infosec Conference Talks Covering AI/ML Security. Talks analyzed in full.
![Kinetic Risk: Securing and Governing Physical AI in the Wild | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/kinetic-risk-securing-governing-physical-ai-padma-apparao.webp)
Learn how physical AI security differs from digital AI risk and why latency is a safety parameter, not a performance metric, in autonomous systems.
![Securing Workspace GenAI at Google Speed | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/genai-agent-security-google-defense-in-depth-blueprint-nicolas-lidzborski.webp)
Learn how Google's Workspace security team built a defense-in-depth architecture against indirect prompt injection and rogue agent actions in production GenAI systems.
![Glass-Box Security: Operationalizing Mechanistic Interpretability | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/glass-box-security-mechanistic-interpretability-for-llms-carl-hurd.webp)
Learn how activation hooks, cosine similarity, and scalar projection enable behavior-based detection inside LLMs — the glass-box security approach to AI threat detection.
![Hooking Coding Agents with the Cedar Policy Language | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/cedar-policy-language-coding-agent-security-matt-maisel.webp)
Learn how to build a Cedar-based policy harness that hooks into Gemini CLI, Claude Code, and Cursor to enforce ABAC rules, track PII taint, and block AI agent data exfiltration.
![Tenderizing the Target | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/synthetic-vulnerability-injection-llm-agents-aaron-grattafiori-skyler-bingham.webp)
Learn how NVIDIAs Project Marinade uses LLM coding agents to inject realistic, tunable vulnerabilities into real codebases - giving you ground-truth benchmarks to evaluate your security tools.
Learn how SuperYARA combines semantic similarity, ML classifiers, and LLM rules to detect prompt injection and GenAI threats at scale — with 99% cost reduction via pre-filtering.
Learn why AI coding tools break EDR detection rules and how to close the intent attribution gap with process ancestry analysis and agent hooks.
![SIFT-FIND EVIL I Gave Claude Code R00t on DFIR SIFT Workstation | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-dfir-14-minutes-claude-code-sift-workstation-rob-t-lee.webp)
Learn how Rob T. Lee gave Claude Code root on the SIFT Workstation and completed a full DFIR investigation — disk image, memory, event logs, MITRE ATT&CK mapping — in under 15 minutes.
![Three Phases of AI Adoption | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/enterprise-ai-adoption-three-phases-hasbrouck-chase-hasbrouck.webp)
Learn the 3 phases of enterprise AI adoption in cybersecurity — and why access, cost, and culture must be solved in order.
![Enterprise AI Governance at Snowflake | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/enterprise-ai-governance-at-scale-snowflakes-model-ragini-ramalingam.webp)
Learn how Snowflake built an enterprise AI governance model that keeps pace with weekly vendor releases and autonomous coding agents — without killing developer productivity.
![Establishing AI Governance Without Stifling Innovation | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-governance-framework-balancing-innovation-risk-billy-norwood.webp)
Learn how to build a tiered AI governance framework that balances enterprise AI security with innovation — from intake scoring to human oversight gates.
Learn how prompt formatting attacks bypass AWS Bedrock Guardrails PII filters without injection — and how system prompt engineering fights back.
![Vibe Check: Security Failures in AI-Assisted IDEs | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-ide-security-failures-vibe-check-unprompted-2026-piotr-ryciak.webp)
Discover how 37 AI-assisted IDE vulnerabilities across 15+ vendors enable zero-click RCE, prompt injection chains, and silent config poisoning — and how to test your tools.
Learn to close the real security gaps in AWS Bedrock and Azure AI defaults — IAM, guardrails, private networking, and confused deputy risks in agentic pipelines.
Learn how attackers exploit Amazon Bedrock agent prompt templates to leak schemas, bypass input validation, and persist malicious instructions across sessions.
![Black-hat LLMs | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/llms-now-find-zero-days-autonomously-nicholas-carlini.webp)
Discover how LLMs now autonomously find and exploit zero-day vulnerabilities in the Linux kernel and Ghost CMS — and what the AI capability curve means for defenders right now.
![Zeal of the Convert: Taming Shai-Hulud with AI | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-assisted-supply-chain-attack-investigation-rami-mccarthy.webp)
Learn how AI workflows, reasoning models, and feedback loops turned a two-week manual investigation into a two-day operation that identified 2,400 supply chain attack victims.
![AI Notetakers: The Most Important Person in the Room | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-notetaker-security-risks-joe-sullivan.webp)
Discover how AI notetakers introduce prompt injection, viral OAuth expansion, and silent recording into your enterprise — and the controls every security team needs now.
![FENRIR: AI Hunting for AI Zero-Days at Scale | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/fenrir-ai-zero-day-vulnerability-discovery-at-scale-peter-girnus-derek-chen.webp)
Discover how Trend Micro's FENRIR engine chains SAST tools, fast LLM triage, and agentic sandboxes to find 60+ CVEs at $8.80 per true positive.
![When Passports Execute: Exploiting AI Driven KYC Pipelines | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/prompt-injection-ai-kyc-pipelines-sean-park.webp)
Learn how attackers embed prompt injections in passport images to hijack AI KYC agents and exfiltrate customer PII at scale.
![Developing & Deploying AI Fingerprints | [un]prompted 2026](https://thecyberarchive.com/assets/teasers/ai-fingerprinting-cross-service-prompt-injection-detection-natalie-isak-waris-gill.webp)
Learn how Binary Shield uses AI fingerprinting to detect and share prompt injection threats across all LLM services in your portfolio — privacy-safe and 36x faster.
![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.
