Black Hat USA 2026 AI Summit
The AI Summit at Black Hat USA 2026 is a one-day event in Las Vegas focused on securing AI systems, AI-enabled threats, digital defense, governance, and regulatory compliance.
AI Engineering // Security // Governance
Practical AI security and policy for systems that act
Independent research notes, red-team methods, and event intelligence for people building, testing, and governing agentic AI systems.
Calendar
Upcoming events
Future talks, workshops, conferences, and community events related to AI systems, security, compliance, and red teaming.
DEF CON 34 / AI Village 2026
AI Village at DEF CON 34 is confirmed for Las Vegas with demos, CTF activity, community programming, and a poster track on adversarial attacks against agents and agentic systems.
AI Risk Summit 2026
AI Risk Summit 2026 brings security and risk executives, AI researchers, policymakers, and developers to Half Moon Bay for two days focused on managing AI risk in practice.
USENIX Security '26
The 35th USENIX Security Symposium brings peer-reviewed systems-security research to Baltimore, with an unusually deep 2026 AI program. Dedicated ML-security sessions cover real-world and indirect prompt injection, adaptive jailbreak attacks, agent memory and resource-abuse failures, LLM privacy and backdoors, and a systematization of agent attacks and defenses; proceedings are open access.
Featured Reading
Current material worth reading
A small, manually reviewed set of technical guides, hands-on exercises, and deep implementation write-ups for testing and securing AI systems in practice.
Hugging Face Diffusers Flaws Could Let Model Repositories Execute Arbitrary Code
Three trust_remote_code bypasses in Hugging Face Diffusers let a crafted model repository execute Python during pipeline loading, including cross-repository, local-snapshot, and time-of-check/time-of-use paths. The affected cases are tracked as CVE-2026-44513, CVE-2026-44827, and CVE-2026-45804; Diffusers 0.38.0 contains the fixes.
Play video
MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef
Chat and coding assistants still hand you walls of text when a button, a chart, or a small interactive view would say it faster.
Play video
When Will The Benchmaxxing Plague End? — Nick Heiner, Surge AI
Every time a model launches there is a gap between the benchmark numbers and what the thing can actually do, and Nick Heiner argues the existence of the word benchmaxxing is the tell.
Play video
MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporal
You invoke a tool and expect an answer, but real work takes time, and over that time connections drop, networks blip, and processes crash.
Understand your AI readiness before the next review.
Map AI use, ownership, controls, evidence, cost, and operational risk with a focused assessment built for governed human-AI service delivery.
24 focused questions
Readiness score
PDF report
Latest Notes
New additions to the research library
Recent notes and references across prompt injection, agent security, evaluations, responsible AI, and adjacent AI work.
Play video
Rethinking Environments for Long-Horizon Work — Rayan Garg, Theta Software
Everyone wants agents that handle long horizon work, but Rayan Garg starts with the awkward question of what long horizon even means.
Play video
Teaching AI to Find Real Vulnerabilities — David Brumley, Bugcrowd
David Brumley has spent two decades turning people into hackers, from founding picoCTF to recruiting pwn2own winners at Carnegie Mellon.
Cloud CISO Perspectives: Why AI Threat Defense is the new boardroom baseline
It’s time to have The Talk: Here’s what boards and CISOs should be discussing on AI-era security governance and business agility.
Chinese Hacker Commands DeepSeek via Telegram to Launch Autonomous Attacks
Palo Alto Networks' Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial Telegram instruction, the agent found internet-facing systems and selected public exploits.
Topic Coverage
Prompt engineering, AI compliance, agent security, and more
These topic hubs connect current engineering and research with the parts of AI security, governance, evaluation, and system behavior that are most useful in practice.
AI Red Teaming
Methods, case studies, and tooling for red teaming AI systems end to end.
Open topicPrompt Engineering
Prompt design patterns, instruction hierarchy, and defensive prompt construction.
Open topicPrompt Injection
Prompt injection attacks, mitigations, detection, and design patterns for safer AI applications.
Open topicAgent Security
Controls and attack paths for browsing, tool use, memory, identity, and action-taking agents.
Open topicModel Evaluation
Safety evaluations, system cards, preparedness, and security measurement for frontier models.
Open topicAI Compliance
Responsible AI, governance, standards, and regulatory reference material for teams mapping AI systems to policy and operational controls.
Open topicAdversarial ML
Adversarial machine learning attacks, taxonomies, and mitigations across the ML lifecycle.
Open topicAI Engineering
Application architecture, developer workflow, tooling, and production patterns for building AI systems.
Open topic
Profile
Profile and contact
Focused on AI engineering, responsible AI, compliance, model behavior, and operational AI systems. Current work includes founding AI operational software for compliance and financial tracking.