AI/LLM Red Teaming & Adversarial Testing
18 curated resources for this skill.
AI Red Teaming Beginners Guide 2026 – Secure AI Systems (Practical DevSecOps)
Long-form guide on what AI red teaming is, attack techniques, and skills; ties to CASP/CAISP certification.
AI Red Teaming — Why & How to Jailbreak LLM Agents (YouTube / TMLS)
Conference talk on multi-turn jailbreak attacks against agents and why continuous automated red teaming is necessary.
AI Red-Teaming & Security Masterclass (LearnPrompting)
Paid masterclass on AI red-teaming and AI security techniques.
Advanced Automated Red Teaming for AI Systems
Expert-level webinar on automated red teaming specifically designed for testing AI and machine learning systems.
Agentic AI Red Teaming | Rob van der Veer & Ken Huang (Cloud Security Alliance)
Cloud Security Alliance experts discuss agentic AI red teaming methodologies and frameworks.
Automating Software Security with LLMs (Offensive Use Cases and Red-Team Style Automation)
Expert deep-dive into using Large Language Models for offensive security automation and red team operations.
Breaking AI: Inside the Art of LLM Pen Testing
Advanced LLM penetration testing focusing on social engineering techniques.
Demo: AI Red Teaming
Hands-on demonstration of AI red teaming techniques and tools in action.
Embedded Jailbreak Templates for Advancing LLM Security (arXiv)
arXiv preprint on Embedded Jailbreak Templates (EJT) for constructing and evaluating jailbreak templates.
FAIRCON25: AI Red Teaming and Risk Analysis Workshop
Two-day workshop at FAIRCON on AI red teaming and risk analysis with 15+ hands-on labs.
How to Do PT for AI: Penetration Testing for AI
GenAI pentesting methodologies and AI vulnerability assessment.
LLM Security – How to Move Fast and Stay Secure (QA webinar)
60-minute webinar on hacking LLM applications, prompt-extraction attacks, and practical defenses.
Lock-LLM Workshop at NeurIPS 2025
Workshop on preventing unauthorized knowledge use from LLMs: un-distillable, un-finetunable, un-compressible, un-editable, un-usable models.
Mastering LLM Integration Security: Offensive & Defensive Tactics (QA)
Two-day, lab-heavy course on exploiting and defending LLM-based systems.
Offensive Security in the Age of AI: Red Teaming LLM (OffSec)
OffSec article on its LLM Red Teaming Learning Path and hands-on labs against LLM deployments.
Secure AI: Red-Teaming & Safety Filters (Coursera)
Design LLM red-teaming scenarios, build adversarial tests, and implement content-safety filters.
What Features in Prompts Jailbreak LLMs? (BlackboxNLP 2025)
Research paper on 10,800 jailbreak attempts and non-linear features that predict jailbreak success.
Break Into AI Testing – Engenious University (Jan 2026 run)
Course on integrating AI-driven assertions, synthetic data, and red-team suites into QA pipelines.