39videosunprompted
13K subscribers on YouTube
Shorts, livestreams, trailers and promos are never listed. Unless a curator approved this channel in full, only individually picked videos appear.
Playlists · 3
26:24Aaron Brown - Trajectory-Aware Post-Training Security Agents | [un]prompted 2026
A 26-minute video from unprompted: “Aaron Brown - Trajectory-Aware Post-Training Security Agents | [un]prompted 2026”.
24:57Adam Krivka & Ondrej Vlcek - AI Found 12 Zero-Days in OpenSSL | [un]prompted 2026
A 25-minute video from unprompted: “Adam Krivka & Ondrej Vlcek - AI Found 12 Zero-Days in OpenSSL | [un]prompted 2026”.
19:02Andrew Bullen - Breaking the Lethal Trifecta (Without Ruining Your Agents) | [un]prompted 2026
Advanced
A 19-minute video from unprompted: “Andrew Bullen - Breaking the Lethal Trifecta (Without Ruining Your Agents) | [un]prompted 2026”.
22:39Arthi Nagarajan - Exploring the AI Automation Boundary | [un]prompted 2026
A 23-minute video from unprompted: “Arthi Nagarajan - Exploring the AI Automation Boundary | [un]prompted 2026”.
23:31Billy Norwood - Establishing AI Governance Without Stifling Innovation | [un]prompted 2026
A 24-minute video from unprompted: “Billy Norwood - Establishing AI Governance Without Stifling Innovation | [un]prompted 2026”.
26:09Bob Rudis & Glenn Thorpe - Detection & Deception Engineering in the Matrix | [un]prompted 2026
A 26-minute video from unprompted: “Bob Rudis & Glenn Thorpe - Detection & Deception Engineering in the Matrix | [un]prompted 2026”.
18:20Brendan Dolan-Gavitt & Vincent Olesen - Agents Exploiting “Auth-by-One” Errors | [un]prompted 2026
A 18-minute video from unprompted: “Brendan Dolan-Gavitt & Vincent Olesen - Agents Exploiting “Auth-by-One” Errors | [un]prompted 2026”.
22:24Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026
A 22-minute video from unprompted: “Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026”.
28:24Carl Hurd - Glass-Box Security: Operationalizing Mechanistic Interpretability | [un]prompted 2026
A 28-minute video from unprompted: “Carl Hurd - Glass-Box Security: Operationalizing Mechanistic Interpretability | [un]prompted 2026”.
23:17Chase Hasbrouck - Three Phases of AI Adoption | [un]prompted 2026
A 23-minute video from unprompted: “Chase Hasbrouck - Three Phases of AI Adoption | [un]prompted 2026”.
29:51Dan Guido - 200 Bugs/Week/Engineer: How We Rebuilt Trail of Bits Around AI | [un]prompted 2026
A 30-minute video from unprompted: “Dan Guido - 200 Bugs/Week/Engineer: How We Rebuilt Trail of Bits Around AI | [un]prompted 2026”.
23:33Daniel Miessler - Anatomy of an Agentic Personal AI Infrastructure | [un]prompted 2026
Advanced
A 24-minute video from unprompted: “Daniel Miessler - Anatomy of an Agentic Personal AI Infrastructure | [un]prompted 2026”.
27:04Dongdong Sun - From OSINT Chaos to Knowledge Graph | [un]prompted 2026
A 27-minute video from unprompted: “Dongdong Sun - From OSINT Chaos to Knowledge Graph | [un]prompted 2026”.
25:24Georgi G - Promp2Pwn - LLMs Winning at Pwn2Own | [un]prompted 2026
Advanced
A 25-minute video from unprompted: “Georgi G - Promp2Pwn - LLMs Winning at Pwn2Own | [un]prompted 2026”.
20:28Heather Adkins & Four Flynn - Evaluating Threats & Automating Defense at Google | [un]prompted 2026
A 20-minute video from unprompted: “Heather Adkins & Four Flynn - Evaluating Threats & Automating Defense at Google | [un]prompted 2026”.
25:58Ilia Shumailov - AI Security with Guarantees | [un]prompted 2026
A 26-minute video from unprompted: “Ilia Shumailov - AI Security with Guarantees | [un]prompted 2026”.
20:42Jeffrey Zhang & Siddh Shah - Guardrails beyond Vibes | [un]prompted 2026
A 21-minute video from unprompted: “Jeffrey Zhang & Siddh Shah - Guardrails beyond Vibes | [un]prompted 2026”.
13:00Jenny Guanni Qu - Why Most ML Vulnerability Detection Fails | [un]prompted 2026
A 13-minute video from unprompted: “Jenny Guanni Qu - Why Most ML Vulnerability Detection Fails | [un]prompted 2026”.
18:31Joey Melo - The Parseltongue Protocol: Textual Obfuscation Methods | [un]prompted 2026
Advanced
A 19-minute video from unprompted: “Joey Melo - The Parseltongue Protocol: Textual Obfuscation Methods | [un]prompted 2026”.
26:05Johann Rehberger - Your Agent Works for Me Now | [un]prompted 2026
A 26-minute video from unprompted: “Johann Rehberger - Your Agent Works for Me Now | [un]prompted 2026”.
22:05Joshua Saxe - The Hard Part Isn’t Building the Agent: Measuring Effectiveness | [un]prompted 2026
A 22-minute video from unprompted: “Joshua Saxe - The Hard Part Isn’t Building the Agent: Measuring Effectiveness | [un]prompted 2026”.
29:12Kyle Polley - Training BrowseSafe: Lessons from Detecting Prompt Injection | [un]prompted 2026
Advanced
A 29-minute video from unprompted: “Kyle Polley - Training BrowseSafe: Lessons from Detecting Prompt Injection | [un]prompted 2026”.
17:14Matt Maisel - Hooking Coding Agents with the Cedar Policy Language | [un]prompted 2026
A 17-minute video from unprompted: “Matt Maisel - Hooking Coding Agents with the Cedar Policy Language | [un]prompted 2026”.
21:57Matt Rittinghouse & Millie Huang - 1.8M Prompts, 30 Alerts | [un]prompted 2026
A 22-minute video from unprompted: “Matt Rittinghouse & Millie Huang - 1.8M Prompts, 30 Alerts | [un]prompted 2026”.
22:17Maxim Kovalsky - The AI Security Larsen Effect: How to Stop the Feedback Loop | [un]prompted 2026
A 22-minute video from unprompted: “Maxim Kovalsky - The AI Security Larsen Effect: How to Stop the Feedback Loop | [un]prompted 2026”.
19:30Mohamed Nabeel - Detecting GenAI Threats at Scale with YARA-Like Semantic Rules | [un]prompted 2026
Advanced
A 20-minute video from unprompted: “Mohamed Nabeel - Detecting GenAI Threats at Scale with YARA-Like Semantic Rules | [un]prompted 2026”.
10:11Mudita Khurana - Rethinking how we evaluate security agents for real-world use | [un]prompted 2026
A 10-minute video from unprompted: “Mudita Khurana - Rethinking how we evaluate security agents for real-world use | [un]prompted 2026”.
18:56Natalie Isak & Waris Gill - Developing & Deploying AI Fingerprints | [un]prompted 2026
A 19-minute video from unprompted: “Natalie Isak & Waris Gill - Developing & Deploying AI Fingerprints | [un]prompted 2026”.
28:42Niki Aimable Niyikiza - Capability-Based Authorization for AI Agents | [un]prompted 2026
A 29-minute video from unprompted: “Niki Aimable Niyikiza - Capability-Based Authorization for AI Agents | [un]prompted 2026”.
20:58Olivia Gallucci - macOS Vulnerability Research | [un]prompted 2026
Advanced
A 21-minute video from unprompted: “Olivia Gallucci - macOS Vulnerability Research | [un]prompted 2026”.
26:58Padma Apparao - Kinetic Risk: Securing and Governing Physical AI in the Wild | [un]prompted 2026
A 27-minute video from unprompted: “Padma Apparao - Kinetic Risk: Securing and Governing Physical AI in the Wild | [un]prompted 2026”.
24:58Paul McMillan & Ryan Lopopolo - Code Is Free: Securing Software | [un]prompted 2026
A 25-minute video from unprompted: “Paul McMillan & Ryan Lopopolo - Code Is Free: Securing Software | [un]prompted 2026”.
21:08Peter Girnus & Derek Chen - FENRIR: AI Hunting for AI Zero-Days at Scale | [un]prompted 2026
Advanced
A 21-minute video from unprompted: “Peter Girnus & Derek Chen - FENRIR: AI Hunting for AI Zero-Days at Scale | [un]prompted 2026”.
24:50Piotr Ryciak - Vibe Check: Security Failures in AI-Assisted IDEs | [un]prompted 2026
A 25-minute video from unprompted: “Piotr Ryciak - Vibe Check: Security Failures in AI-Assisted IDEs | [un]prompted 2026”.
16:24Roey Ben Chaim - Total Recon: How We Discovered 1000s of Open Agents in the Wild | [un]prompted 2026
A 16-minute video from unprompted: “Roey Ben Chaim - Total Recon: How We Discovered 1000s of Open Agents in the Wild | [un]prompted 2026”.
26:11Scott Behrens & Justice Cassel - Source to Sink: Improving LLM Vuln Discovery | [un]prompted 2026
Advanced
A 26-minute video from unprompted: “Scott Behrens & Justice Cassel - Source to Sink: Improving LLM Vuln Discovery | [un]prompted 2026”.