Offensive AI Con

Year 2 of the first con dedicated to exploring the offensive use of AI.
Hosted by RemoteThreat.

Oct 4-7, 2026 | Oceanside, CA
#OffensiveAICon

[Offensive AI Con @OffensiveAIcon]

New talk up from OAIC 2026: I Know What You Didn’t Fix Last Summer with @dyn___ Aaron Grattafiori of @Umbriel_AI

What if the next vulnerability is hiding in a patch that already shipped? Aaron shows how LLMs can uncover incomplete fixes and related bug variants- and how to validate what they find.

Watch the full talk:
https://t.co/t4uHIK4sYe

#OAIC #OffensiveAI #VulnerabilityResearch

[Offensive AI Con @OffensiveAIcon]

New talk up OAIC 2026: Vibe Fuzzing with Sam Lovejoy @_dinolover38 of IBM X-Force Offensive Research.

Sam explores how graph-based inputs, program state, and LLM guidance come together in an AI-guided fuzzing engine- and the tradeoffs behind it.

Watch the full talk: https://t.co/zFcLR5AvZd

#OAIC #OffensiveAI #Fuzzing

[Offensive AI Con @OffensiveAIcon]

Now up from OAIC 2026: Teaching Agents to Escape with Dr. Gaspard Baye, Ph.D Baye of Valix AI.

A closer look at command evasion, reinforcement learning, and the limits of agent sandboxes.

Watch the full talk here:
https://t.co/xA5MOT3Q6O

#OAIC #OffensiveAI #AISecurity

[Offensive AI Con @OffensiveAIcon]

How do you turn AI-powered vulnerability discovery into a reliable system for large codebases?

Alex Tselevich and Michael Maturi from @Mandiant share practical lessons from building agentic harnesses for static analysis. They cover threat modeling, lead selection, context and token management, agent orchestration, deduplication, validation, and benchmarks that measure real improvements.

Watch their OAIC 2026 talk below. 👇
https://t.co/htE0BLk9qJ

#OAIC #OffensiveAI #Evals

[Offensive AI Con @OffensiveAIcon]

Your EDR Has Boundary Issues.

@harmj0y and @tifkin_ of @SpecterOps explore how adversarial machine learning can evade EDR detection- and how LLMs are accelerating the reverse engineering behind it.

Watch their Offensive AI Con talk below. 👇
https://t.co/cwnirhS595

#OAIC #OffensiveAI #Cybersecurity #EDR

[Offensive AI Con @OffensiveAIcon]

Stop Giving Models Open-Book Tests.

Matthew Nickerson of @SpecterOps introduces the Offensive Reasoning Index (ORI), a BloodHound-based benchmark for testing whether AI models can discover valid attack paths in unfamiliar Active Directory graphs.

Watch his OAIC 2026 talk below. 👇

https://t.co/7f5HyKsOAp

#OAIC #OffensiveAI #Cybersecurity

[RemoteThreat @RemoteThreat]

Monday night at OAIC, we took the conversation to the rooftop.

Pacific sunsets. Poolside drinks. Great conversations that kept going long after dark.

RemoteThreat proudly sponsored the party, where many of the sharpest minds in offensive AI and security came together to swap ideas, catch up with old friends, and make new ones. Researchers whose work we’ve followed for years, people we’d only met online, and plenty of first introductions.

That’s what made the night: the people, the curiosity, and the generosity to share what they’re learning.

Thanks to everyone who joined us and made this community what it is. 🤙

#OAIC #OffensiveAI #RemoteThreat

[Offensive AI Con @OffensiveAIcon]

The OAIC keynote video is live!

Thank you to David Brumley for an excellent keynote, “AI Exploitation, Quantified,” and for giving us plenty to think about as frontier labs push AI’s cyber capabilities forward.

Watch here: https://t.co/5vhEeA7I7T

[Aaron Grattafiori @dyn___]

This was a great talk at OAIC by @_dinolover38 and some really cool techniques. Fuzzing is dead, long live fuzzing.

[Aaron Grattafiori @dyn___]

This was a great set of talks at @OffensiveAIcon by @shanejcaldwell and @0xdab0 plus Michael Kouremetis yesterday... definitely check out the papers and research.

[dreadnode @dreadnode]

About last night..! Dreadnode was the sponsor of the @OffensiveAIcon Welcome Party.

A gorgeous sunset, @bradpalmtree's DJ set, Oceanside Pier-inspired airbrush art, Hackin' Kraken blood orange margaritas, plus an incredible community of offensive AI researchers and innovators. We're proud to be a part of it.

In town for #OAIC? Don't sleep on the final talk of the day: @mkultraWasHere hits the stage today at 4:40 PM for "All Models Cheat: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks".

[Offensive AI Con @OffensiveAIcon]

Our friends at @dreadnode are hosting the kick-off party for OAIC 2026! We're excited to kick off year two at the Seabird Poolside Lounge, with good food, incredible vibes, and a few special surprises. 👀

[Offensive AI Con @OffensiveAIcon]

OAIC starts off tomorrow! Day 2 wraps up with Joe Miller, Gaspard Baye, Ph.D, Alex Tselevich & Michael Maturi, Moni Pande & Niru Ragupathy, and finally a restricted session by National Cyber Security Centre on the Threat of Adversary Us Of Offensive AI.

#OAIC #OffensiveAICon

[Offensive AI Con @OffensiveAIcon]

Thank you to @trailofbits for sponsoring OAIC 2026! They recently published research where they gave GPT 5.6-Cyber one task: escape a QEMU/KVM VM used to sandbox agents. In its final escape, the agent chained three 0-days into a working exploit.

https://t.co/PwZYIcP0cg

[Offensive AI Con @OffensiveAIcon]

Oceanside is under a heat warning this week! As always, OAIC is casual- shorts and sandals are strongly encouraged! ☀️🩴

[Offensive AI Con @OffensiveAIcon]

Thank you to our Gold Sponsor, @CodeWall_AI!

#OAIC #AI #OffensiveAICon @darkp0rt

[Offensive AI Con @OffensiveAIcon]

Just two weeks until OAIC! Will Schroeder, Lee Chagolla-Christensen, Becca Lynch, Matthew Nickerson, Max Bazalii, and Aaron Grattafiori are up the first half of day 1!

See the full agenda at https://t.co/CPMwxOtaOQ

[Offensive AI Con @OffensiveAIcon]

The sun is setting on submissions for OAIC 2026. The Call for Papers closes July 31.

We are looking for original, practical research advancing the offensive use of AI, presented by the researchers and practitioners doing the work.

Join us seaside in San Diego