Talks learning path

Orientation and first principles — what the bug class is and how it behaves.

1. AI Agent Security Masterclass: Attacking and Defending Autonomous AI Systems - DEF CON Training
   27 min readtraining.defcon.org2026
   Training covers attacking and defending autonomous AI agents, focusing on building secure agents, exploiting weaknesses, and implementing defenses against prompt injection, excessive agency, tool misuse, and MCP-based supply chain attacks. Participants will learn about AI agent architecture, RAG security, threat modeling AI systems, and practical red-teaming exercises against vulnerable agents, culminating in defense strategies like least privilege, sandboxing, and robust prompt controls.
2. Hacking Android and IOT Apps by Example - DEF CON Training LV 2026
   9 min readtraining.defcon.org2026
   Workshop slides from DEF CON LV 2026 detail hands-on techniques for hacking Android and IoT applications, focusing on the OWASP Mobile Security Testing Guide (MSTG) and MASVS. Participants will learn static and dynamic analysis methods, advanced instrumentation with Frida, Objection, and radare2, and how to bypass common security controls like certificate pinning and root detection. The training covers identifying vulnerabilities through app analysis without device access, efficient exploitation, and leveraging open-source tools for mobile security testing.
3. Frans Rosén Keynote at BSides Ahmedabad - YouTube
   youtube.com2025
   Frans Rosén delivered a keynote speech at BSides Ahmedabad, which is available on YouTube. The content likely includes insights, information, or perspectives shared by Frans Rosén during the keynote address at the event. Viewers can watch the video to gain knowledge or understanding of the topics discussed by Frans Rosén at BSides Ahmedabad.
4. Irit Katriel- opening keynote: Error Handling: From Charles Babbage to Python 3.11
   youtube.com2023
   Irit Katriel- opening keynote: Error Handling: From Charles Babbage to Python 3.11 https://www.youtube.com/watch?v=rKBKHVvXuUI
5. GitHub - schwartz1375/genai-security-training
   3 min readgithub.com2026
   Library of self-paced training modules for red teaming GenAI and AI/ML systems, covering adversarial attacks, privacy breaches, model manipulation, and system-level exploits like prompt injection and jailbreaking. It includes hands-on labs, theoretical content, and practical demonstrations utilizing tools such as the Adversarial Robustness Toolbox (ART), TextAttack, and SHAP, while also referencing OWASP LLM Top 10 and MITRE ATLAS frameworks.

Real testing methodology, tooling, and writeups that show the work.

1. Write Once, Shell Everywhere - Turning Arbitrary File Writes into RCE (DEF CON Bug Bounty Village)
   20 min readethiack.com2026
   Library cataloging techniques for escalating arbitrary file writes to remote code execution, focusing on modern, stripped-down environments. It categorizes existing methods by operating system, language runtime, and framework, evaluating their usefulness in contemporary security engagements. Specific techniques discussed include leveraging `/etc/ld.so.preload` and identifying vulnerabilities within language runtime deserialization processes, offering practical insights for discovering and exploiting file write primitives.
2. [HackerNotes Ep.95 & Ep.96] Cookies, Caching & Attacking Chrome Extensions with MatanBer
   21 min readblog.criticalthinkingpodcast.io2024
   Library detailing attacks against Chrome Extensions, covering their components like content scripts, service workers, extension pages, and manifest files. It explains how to gain access to extension source code, identifies attack vectors for content scripts including DOM injection and clickjacking, and discusses attacking extension pages and service workers via misconfigurations in `web_accessible_resources` and `externally_connectable`. The entry also touches on debugging techniques and includes references to Heroctf-v6 writeups concerning cache API and service worker research.
3. Securing next-gen development: Lessons from Trust Bank and TASConnect
   6 min readsnyk.io2026
   Talk from Black Hat Asia featuring experts from Trust Bank and TASConnect, discussing strategies for securing next-generation applications. It highlights the challenges posed by complex architectures, AI-generated code (like that from GitHub Copilot and Google Gemini), and multi-cloud deployments. The session emphasizes a proactive, developer-first approach, leveraging tools such as Snyk for immediate feedback and risk prioritization, and tracking key metrics like security training implementation and time to remediate to align security with business goals.
4. Slides: GraphQL Hacking
   rashahacks.com2023
   Slides: GraphQL Hacking https://ift.tt/oLqt1GD
5. Web App Pentesting in the AI Era
   18 min readblog.includesecurity.com2026
   Library for AI-assisted web application security testing, detailing practical experiences with frontier and local models. This resource breaks down AI systems into models, inference engines, and harnesses, and explores their capabilities for vulnerability discovery. It highlights the importance of a three-way alignment between model, harness, and task, emphasizing that even advanced AI output requires human review for accuracy. The entry discusses building a simple harness to improve thoroughness and validation, advocating for execution-grounded proofs-of-concept over AI-generated reasoning, and notes the rapid evolution of AI tools in the cybersecurity landscape.

Novel research, edge cases, and the techniques that push the class forward.

1. Can AI do novel security research? Meet the HTTP Terminator
   29 min readportswigger.net2026
   Tool: The HTTP Terminator, an autonomous security research system, explores the frontier of AI-driven bug hunting. It generates novel HTTP desync triggers, gadgets, and exploits, demonstrating novel attack techniques that compromised live systems. The tool analyzes discovery chains, enabling the transformation of human expertise into autonomous weapons, and identifies research areas beyond current AI capabilities, including undisclosed recon techniques and new attack classes. Presented at Black Hat USA 2026 and DEF CON 34, the HTTP Terminator's open-source release is intended to help other researchers adopt this automated approach.