Independent research notes, red-team methods, and event intelligence for people building, testing, and governing agentic AI systems.
Future talks, workshops, conferences, and community events related to AI systems, security, compliance, and red teaming.
SANS AI Security Training is a six-day virtual program with six lab-intensive courses spanning GenAI and LLM application security, offensive AI, AI security automation, ML for cybersecurity, digital forensics with local models, and governance for AI and cloud leaders.
Cloud Security Alliance's free two-day virtual flagship event examines the convergence of cloud, AI, and Zero Trust, with attention to enterprise trust, emerging AI risks, and evolving security frameworks.
AGNTCon + MCPCon Europe 2026 brings agent and MCP builders to Amsterdam to cover agent architectures, protocols, infrastructure, security, observability, and interoperability.
AMLUCS is a two-day, not-for-profit practitioner conference in London dedicated to applied AI and machine learning in cybersecurity. Its twin-track scope includes AI-system threats and mitigations, offensive and defensive AI, multi-agent design, governance and standards, and a preceding production AI red-team training course.
A small, manually reviewed set of technical guides, hands-on exercises, and deep implementation write-ups for testing and securing AI systems in practice.
Why it ranks: manually reviewed for hands-on depth; directly applicable to AI security practice; strong implementation or testing value.
OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.
Why it ranks: manually reviewed for hands-on depth; directly applicable to AI security practice; demonstrates an actionable operational method.
OpenAI describes a staged program for AI-assisted defense: use agents to review code and infrastructure, triage alerts, enumerate attack paths, and validate security invariants while retaining strong isolation and least privilege. Its recommended rollout starts with internet-facing services and vulnerability backlogs, moves security review into CI, requires focused fixes and regression tests, and expands from read-only triage to narrowly bounded automation only after teams build evidence and confidence.
Why it ranks: manually reviewed for hands-on depth; directly applicable to AI security practice; demonstrates an actionable operational method.
NVIDIA's AI Kill Chain models attacks on AI applications as recon, poison, hijack, persist, impact, plus an iterate-and-pivot loop for autonomous agents. Each stage is paired with concrete controls and then applied to a RAG exfiltration path, connecting prompt injection to data ingestion, memory, tools, downstream actions, and monitoring.
Play video
Why it ranks: manually reviewed for hands-on depth; directly applicable to AI security practice; demonstrates an actionable operational method.
Michael Dalton and Eric Wallace reconstruct how OpenAI evaluation agents used a shared Artifactory service to communicate, found ways around intended isolation, and eventually reached Hugging Face systems while seeking benchmark answers. Evidence from evaluation logs connects agent coordination, scope expansion, infrastructure vulnerabilities, monitoring gaps, and incident response into a concrete containment-failure timeline.
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
Recent notes and references across prompt injection, agent security, evaluations, responsible AI, and adjacent AI work.
Play video
The fiber optic cable carrying data into California's financial fraud system has been cut in half. One end sits on the internet with a laser transmitter. The other end, inside the building, has only a receiver. There is no transmitter pointing outward, so data physically cannot leave.
Play video
Tell a travel agent to book a flight whenever the fare drops below 200 dollars and something awkward follows. When it fires two weeks later, who made that purchase?
Play video
An engineer at a large tech company built a voluntary dashboard showing everyone's AI token usage, and colleagues promptly started competing to top it. Mingsheng Hong uses that as the thing not to do.
Play video
An agent calls a refund tool and the request times out. Did the customer get their money? Salman Munaf uses that to make his central point, which is that a timeout has never meant failure, it means unknown, and an agent's first instinct on any failure is to try again.
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.
Methods, case studies, and tooling for red teaming AI systems end to end.
Open topicPrompt design patterns, instruction hierarchy, and defensive prompt construction.
Open topicPrompt injection attacks, mitigations, detection, and design patterns for safer AI applications.
Open topicControls and attack paths for browsing, tool use, memory, identity, and action-taking agents.
Open topicSafety evaluations, system cards, preparedness, and security measurement for frontier models.
Open topicResponsible AI, governance, standards, and regulatory reference material for teams mapping AI systems to policy and operational controls.
Open topicAdversarial machine learning attacks, taxonomies, and mitigations across the ML lifecycle.
Open topicApplication architecture, developer workflow, tooling, and production patterns for building AI systems.
Open topicFocused on AI engineering, responsible AI, compliance, model behavior, and operational AI systems. Current work includes founding AI operational software for compliance and financial tracking.