AI
📕 Your AI Agent Has Production Access: Now What? 🔥
ai securitydefensive security
Topic
AI Security
Attacking and defending AI systems — prompt injection, jailbreaks, AI red teaming, agent security, guardrails, and AI-supply-chain risk.
- LLM security
- prompt injection
- jailbreaking
- AI red teaming
- model poisoning
- training data attacks
- adversarial machine learning
- AI supply chain
- AI-powered attacks
- deepfake detection
- AI governance
- securing AI pipelines
- agent security
- guardrails
- AI-assisted vulnerability discovery
154
Talks
9
Conferences
BSidesSF 2026
22 talksThe Show Must Go On: Putting on The BSidesSF Program
ai securityapplication security
📗 How We Red-Teamed Our Own AI Agent: Lessons from Operation Pale Fire 🤖
ai securityoffensive security
📙 The Great Credential Caper: How to Perform and then Defend Against the (Nearly Impossible) to Defend 🏗️
offensive securityapplication securityai security
📙 One Thousand and One AI-Prevented CVEs: Vibe Coding a Whole New Supply Chain Defense 🤖
application securityai security
📙 From Assistant to Assassin: Weaponizing An OpenClaw Vulnerability to Achieve 1-Click RCE 🖥️
offensive securityai security
📕 Security for AI Agents Using an Ensemble of Fine-tuned Small Language Models 🤖
ai security
🎤 Architecting the Modern SOC: The Evolving AI Reality for Blue Teams 🔥
defensive securityai securitygovernance and risk
📙 Not My Vibe: When AI Coding Agents Go Off the Rails 🤖
ai securityapplication security
📙 From Noise to Notes: Orchestrating SAST with Developers through AI-Driven Remediation 🖥️
application securityai security
📕 Pwning and Defending AI Agent Code Interpreters 🤖
offensive securitycloud securityai security
CISO Series Live Podcast Recording
security leadershipgovernance and riskai security
📙 Reverse Engineering Go Malware: From Manual to AI-Powered Analysis 🤖
malware and threat intelai security
AI for security - friend or foe?
ai securitydefensive security
📙 Saving Bug Bounties from AI Slop 🤖
offensive securityai security
📙 AI as an Accountable Entity: Governing Risk When Machines Make Decisions ⚖️
ai securitygovernance and risk
📕 Making WAF Mainstream: From Static Defenses to Living, Learning Protection 🖥️
application securityai security
📙 Increasing the Analysis Surface of Large Language Models 🤖
ai security
📙 Detection Allegro: Composing Detection Rules with Agentic Workflows 🔥
defensive securityai security
📙 Conducting the Kill-Chain: Detecting APT Progression Through Music-Sequence Modeling 🤖
defensive securityai security
Prompt, Commit, Repeat: Security at Scale When 1,000 Devs Go AI-Native
ai securityapplication security
📕 AI-Powered AppSec: 10x Your Security Team Without Scaling Headcount 🖥️
application securityai security
What LLMs Do, and Don't, Know About Securing Kubernetes - Rory McCune, Datadog
cloud securityai securityoffensive security
Privacy as Infrastructure: Declarative Data Protection for AI on Kubernetes - Joaquin Rodriguez, Microsoft & Krishnendu Dasgupta, AXONVERTEX AI
cloud securityai securitygovernance and risk
[un]prompted 2026
52 talks"Can You See What Your AI Saw?": GenAI Endpoint Observability for Detection Engineers
defensive securityai security
AI Found 12 Zero-Days in OpenSSL | [un]prompted 2026
ai securityoffensive security
AI Notetakers: The Most Important Person in the Room
ai securitygovernance and risk
Daniel Miessler - Anatomy of an Agentic Personal AI Infrastructure | [un]prompted 2026
ai security
Nicholas Carlini - Black-hat LLMs | [un]prompted 2026
offensive securityai security
Code Is Free: Securing Software in the Agentic Future
ai securityapplication security
Detecting GenAI Threats at Scale with YARA-Like Semantic Rules
ai securitydefensive security
Natalie Isak & Waris Gill - Developing & Deploying AI Fingerprints | [un]prompted 2026
ai securitydefensive security
Ragini Ramalingam - Enterprise AI Governance at Snowflake | [un]prompted 2026
governance and riskai security
Establishing AI Governance Without Stifling Innovation: Lessons Learned
governance and riskai security
Heather Adkins & Four Flynn - Evaluating Threats & Automating Defense at Google | [un]prompted 2026
application securityai security
FENRIR: AI Hunting for AI Zero-Days at Scale
ai securityoffensive security
Glass-Box Security: Operationalizing Mechanistic Interpretability for Defending AI Agents
ai securitydefensive security
Guardrails beyond Vibes: Shipping Security Agents in Production
ai securityapplication security
Hooking Coding Agents with the Cedar Policy Language
ai securitygovernance and risk
Kinetic Risk: Securing and Governing Physical AI in the Wild
ai securitygovernance and risk
Rob T. Lee - SIFT-FIND EVIL! I Gave Claude Code R00t on DFIR SIFT Workstation | [un]prompted 2026
defensive securityai security
Security Guidance as a Service: Building an AI-Native Blueprint for Defensive Security
application securityai security
Aaron Grattafiori & Skyler Bingham - Tenderizing the Target | [un]prompted 2026
ai securityoffensive security
The AI Security Larsen Effect: How to Stop the Feedback Loop
ai securitygovernance and risk
Joshua Saxe - The Hard Part Isn’t Building the Agent: Measuring Effectiveness | [un]prompted 2026
ai securitydefensive security
Three Phases of AI Adoption: From GPU Lottery to Enterprise Agreements
ai securitygovernance and risk
Aaron Brown - Trajectory-Aware Post-Training Security Agents | [un]prompted 2026
ai securityoffensive security
Piotr Ryciak - Vibe Check: Security Failures in AI-Assisted IDEs | [un]prompted 2026
ai securityapplication security
When Passports Execute: Exploiting AI Driven KYC Pipelines
ai securityoffensive security
Zeal of the Convert: Taming Shai-Hulud with AI
ai securitymalware and threat intel
Matt Rittinghouse & Millie Huang - 1.8M Prompts, 30 Alerts | [un]prompted 2026
ai securitydefensive security
Dan Guido - 200 Bugs/Week/Engineer: How We Rebuilt Trail of Bits Around AI | [un]prompted 2026
ai securityapplication security
Sergej Epp - 8 Minutes to Admin. We Caught It in the Wild. | [un]prompted 2026
ai securitydefensive security
Ilia Shumailov - AI Security with Guarantees | [un]prompted 2026
ai security
Andrew Bullen - Breaking the Lethal Trifecta (Without Ruining Your Agents) | [un]prompted 2026
ai security
Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026
ai security
Capability-Based Authorization for AI Agents: Warrants That Survive Prompt Injection
ai securityidentity and access
Arthi Nagarajan - Exploring the AI Automation Boundary | [un]prompted 2026
ai securitydefensive security
Flash Talks | [un]prompted 2026
ai securitydefensive security
From OSINT Chaos to Knowledge Graph: Building Production-Scale AI-Powered Threat Intelligence
malware and threat intelai security
Srajan Gupta - Injecting Security Context During Vibe Coding | [un]prompted 2026
application securityai security
Are you thinking what I'm thinking?
ai security
Traditional ML vs LLMs: who can classify better?
ai securitynetwork and infrastructure
Operation Pale Fire: How We Red-Teamed Our Own AI Agent
ai securityoffensive security
Gadi Evron on behalf of Zenity - PleaseFix | [un]prompted 2026
ai securityoffensive security
Georgi G - Promp2Pwn - LLMs Winning at Pwn2Own | [un]prompted 2026
offensive securityai security
Rethinking how we evaluate security agents for real-world use
ai security
Securing Workspace GenAI at Google Speed: Surviving the Perfect Storm
ai security
Source to Sink: How to Improve LLM First-Party Vuln Discovery
ai securityapplication security
The Parseltongue Protocol: A Deep Dive into 100+ Textual Obfuscation Methods
ai securityoffensive security
Total Recon: How We Discovered 1000s of Open Agents in the Wild
ai securityoffensive security
Training BrowseSafe: Lessons from Detecting Prompt Injection in Production Browser Agents
ai securitydefensive security
Rob T. Lee, Glenn Thrope, Dan Hubbard & Sergej Epp - Vibe Coded | [un]prompted 2026
ai securityoffensive securitydefensive security
Why Most ML Vulnerability Detection Fails (And What Actually Worked for Kernel Bugs)
ai securitydefensive security
Johann Rehberger - Your Agent Works for Me Now | [un]prompted 2026
ai security
Olivia Gallucci - macOS Vulnerability Research | [un]prompted 2026
offensive securityai security
NDC Security 2026
12 talksWon't somebody please think of the children!?
governance and riskai security
AppSec Security: The SDLC in the age of agentic
application securityai security
Keynote: 25 Years of the Microsoft SDL
application securityai security
Prompt Hardening - Secure Code Generation Using AI
application securityai security
The Risky Business, of AI Illiteracy
ai securitygovernance and risk
MCP Security: Keep Your AI Agents from Spilling the Tea
ai securitycloud securityidentity and access
Hijacking Google's CI/CD Through Prompt Injection: The New Era of AI-Based Exploits
ai securityapplication security
Beyond Trust: Building Community-Driven Security Analysis for Your .NET Software Supply Chain
application securityai security
Breaking the Black Box: Why Testing Generative AI Is Full Spectrum
ai security
Who Gave the Agent Admin Rights?! Securing Cloud & AI Machine Identities
ai securityidentity and access
Attacking AI
ai securityapplication security
Securing Code in the Age of AI
application securityai security
DefCamp 2025
7 talksOffensive Security - Automation and AI at DefCamp 2025
offensive securityai security
RAGe Against the Machine: AI-Powered Compliance and Cybersecurity at DefCamp 2025
governance and riskai security
Hacking Dictatorships with AI: Real-World Cases of Digital Sabotage and Propaganda Warfare
offensive securityai security
From Prompt to Payload: Breaking GenAI with Real-World MCP Exploits at DefCamp 2025
ai securityoffensive security
Trust No Format: Risks and Defenses for ML Model Serialization at DefCamp 2025
ai securityoffensive security
Lets make the LLM a Defector: Deceiving LLM into Attacking its Own Agent through natural language
ai securityoffensive security
Beyond Scanning - Why Vulnerability Assessment Isn't Sufficient for Attack Surface Management
defensive securityai security
OWASP Global AppSec USA 2025
4 talksIndirect Prompt Injection: Architectural Testing Approaches for Real World AI/ML Systems
ai securityapplication securityoffensive security
The Future of AppSec is Continuous Context (Keynote)
ai securityapplication securitysecurity leadership
Attacking AI
offensive securityai security
OWASP AIVSS Project: What it is, why we need it and how we are doing it
ai securitygovernance and risk
DEF CON® 33 Hacking Conference
22 talksHow AI + Hardware can Transforming Point-of-Care Workflows
mobile and iot securityai security
Beyond Assistants: Securing Agentic AI Systems and Multi-Agent Workflows in High-Stakes Environments
ai securityapplication security
The Price for Progress: Ethical Cybersecurity and Tech-Driven Communities
governance and risksecurity leadershipai security
Of Stochastic Parrots and Deterministic Predators: Decision-Making in Adversarial Automation
offensive securityai security
AppleStorm - Unmasking the Privacy Risks of Apple Intelligence
ai securitymobile and iot security
Vibe School: Making dumb devices smart with AI
mobile and iot securityai security
Invitation Is All You Need! Invoking Gemini for Workspace Agents with a Simple Google Calendar Invite
ai securityoffensive security
Deepfake Image and Video Detection
ai securitydefensive security
Loading Models, Launching Shells: Abusing AI File Formats for Code Execution
ai securityoffensive security
Voice Cloning Air Traffic Control: Vulnerabilities at Runway Crossings
network and infrastructureai security
Let AI Auto-Generate Neural-ASR Rules for OT-specific Attacks via NLP Approach
defensive securityai security
Hacking Reality: HoloConnect AI and the Rise of Offline Holograms in Medical Devices
ai securitymobile and iot security
Orion - fuzzing workflow automation
offensive securityai security
Mind the Data Voids: Hijacking Copilot Trust to Deliver C2 Instructions with Microsoft Authority
ai securityoffensive security
Illuminating the Dark Corners of AI: Extracting Private Data from AI Models and Vector Embeddings
ai securityoffensive security
They deployed Health AI on us. We’re bringing the rights & red teams.
ai securityoffensive securitygovernance and risk
Securing Intelligence: How hackers are breaking modern AI systems … and how bug bounty programs can keep up
ai securityoffensive security
Closing Patient Safety Gaps with Smart Tech and AI
ai securitydefensive security
Hacking Context for Auto Root Cause and Attack Flow Discovery
defensive securityai security
Prompt. Scan. Exploit: AI’s Journey Through Zero-Days and a Thousand Bugs
offensive securityai security
Thinking Like a Hacker in the Age of AI
ai securityoffensive security
Patching Critical Infrastructure: Announcing the Winners of DARPA’s AI Cyber Challenge
ai securityapplication security
Black Hat USA 2025
22 talksBlack Hat USA 2025 | From Prompts to Pwns: Exploiting and Securing AI Agents
ai securityoffensive security
When Guardrails Aren't Enough: Reinventing Agentic AI Security With Architectural Controls
ai security
Cybersecurity, AI, and Our Brains. A Fireside Chat with Cognitive Scientist and AI Expert Gary Marcus
ai security
Adversarial Fuzzer for Teleoperation Commands: Evaluating Autonomous Vehicle Resilience
mobile and iot securityai security
LLMs-Driven Automated YARA Rules Generation with Explainable File Features & DNAHash
malware and threat intelai security
How Tree-of-AST Redefines the Boundaries of Dataflow Analysis
offensive securityai security
Autonomous Timeline Analysis and Threat Hunting: An AI Agent for Timesketch
defensive securityai security
Universal and Context-Independent Triggers for Precise Control of LLM Outputs
ai securityoffensive security
AI Enterprise Compromise - 0click Exploit Methods
ai securityoffensive security
Invitation Is All You Need! Invoking Gemini for Workspace Agents with a Simple Google Calendar Invite
ai security
Black Hat USA 2025 | Advanced Bypass Techniques and a Novel Detection Approach
ai securitydefensive security
The New Frontline: Cyber on the Precipice
malware and threat intelai security
Evil Digital Twin, Too: The First 30 Months of Psychological Manipulation of Humans by AI
ai securityoffensive security
Hack to the Future: Owning AI-Powered Tools with Old School Vulns
ai securityapplication security
AI Agents for Offsec with Zero False Positives
ai securityoffensive security
Black Hat USA 2025 | More Flows, More Bugs: Empowering SAST with LLMs and Customized DFA
application securityai security
Training Specialist Models: Automating Malware Development
ai securitymalware and threat intel
BinWhisper: LLM-Driven Reasoning for Automated Vulnerability Discovery Behind Hall-of-Fame
ai security
Let LLM Learn: When Your Static Analyzer Actually 'Gets It'
application securityai security
Clue-Driven Reverse Engineering by LLM in Real-World Malware Analysis
malware and threat intelai security
Unveiling the Hidden Perils of the TorchScript Engine in PyTorch
application securityai security
Locknote: Conclusions & Key Takeaways from Black Hat USA 2025
ai security
OWASP Global AppSec USA 2024
11 talksOWASP Top 10 for Large Language Models: Project Update
ai securityapplication securitygovernance and risk
Living off Microsoft Copilot
offensive securityai security
Escaping Vulnerability Hell: Bridging the Gap Between Developers and Security Teams
application securityai security
AI Code Generation - Benefits, Risks and Mitigation Controls
application securityai securitygovernance and risk
Thriving in the Age of AI (Keynote)
ai securitysecurity leadership
Don't Make This Mistake: Painful Learnings of Applying AI in Security
application securityai security
Red, Blue, and Purple AI (Keynote)
offensive securitydefensive securityai security
AI Under the Hood: Unmasking Hidden Threats
ai securityapplication security
Threat Modeling in the Age of AI
ai securityapplication security
AI Goat: A Damn Vulnerable AI Infrastructure
ai securitycloud securityoffensive security
OWASP AI Exchange experts on the future of security for AI
ai securitygovernance and riskapplication security