DEF CON 34 Notes: 15 Talks on AI Security, Agentic Systems, and Red Teaming
I spent DEF CON 34 bouncing between the talks from the AI Village, Adversary Village, and main tracks. Almost every talk I sat in on had a similar throughline: agents…
I spent DEF CON 34 bouncing between the talks from the AI Village, Adversary Village, and main tracks. Almost every talk I sat in on had a similar throughline: agents…
Speaker: Chen Doytshman, security researcher (AI/ML background) ยท Source: Unit 42 research article ๐ Download this note as Markdown Overview In November 2025, Anthropic disclosed a state-sponsored operation where AI…
Speakers: Xia Hua (co-founder/CEO, Traceforce), Abhijeet Kumar (OSCP, UMD CTF captain) ยท GitHub: mcp-xray ๐ Download this note as Markdown Overview Agents now run with thousands of third-party plugins โ…
Source: DEF CON 34 talk page ยท GitHub: respondent-community ๐ Download this note as Markdown Overview Most vibe-coding demos stop at TODO apps and landing pages. This 150-minute workshop went…
Speakers: Thomas Mason, Tahseen Rabbani ยท GitHub: WAVES (synthid-regen-kit) ๐ Download this note as Markdown Overview Google's SynthID watermark invisibly tags content generated by its models (Nano Banana, Gemini, etc.)…
Speakers: Langston Clement, Dan Goga ยท Source: DEF CON 34 talk page ยท GitHub: sh0cksec ๐ Download this note as Markdown Overview Traditional RFID badge cloning methods require you to…
Source: Adversary Village talk page ยท GitHub: Red_Agent_Workshop ๐ Download this note as Markdown Overview With recent advances in AI, LLMs are increasingly applied to red team engagements โ but…
Speaker: Stav Cohen, AI Security Research Lead at Zenity and PhD student at the Technion ยท Source: DEF CON 34 talk page ๐ Download this note as Markdown Overview Stav…
Speaker: Kevin "kdrwins" Dela Rosa (previously Snapchat, Amazon; now CTO at Cloudglue) ยท Source: DEF CON 34 talk page ยท GitHub: overcast ยท URL: overcast.video ๐ Download this note as…
Speakers: Lee McWhorter, Alexander "Zombie" ยท Source: DEF CON 34 talk page ๐ Download this note as Markdown Overview AI defenses are only as good as the analysts training them.…