Day: ?? . Time: ?? SGT
A Year of Hacking with LLMs: A Practitioner's Reflections
Dr. Edward PengHuazhong University of Science and Technology (HUST)
0x00//PROGRAMME — TALK BOARD
The Line-Up
// one single track.
More talks to come. Reviewed by a peer-review board of practising researchers. Click any talk for details — share the link with a colleague.
Day: ?? . Time: ?? SGT
The Chaos Phase or How I Learned to Stop Worrying and Love Offensive AI
Nico WaismanXBOW
Day: ?? . Time: ?? SGT
I Let A.I. Loose on Google. It Found RCE. Twice.
Arvin ShivramBrutecat Security Pte Ltd
Day: ?? . Time: ?? SGT
From CloseHandle to Code Execution: Exploiting an arbitrary handle close vulnerability for EOP
Arjun VasudevaMicrosoft
Day: ?? . Time: ?? SGT
Chaining Logical Bugs for Reliable Windows LPE
Bocheng Xiang , HeeChan KimFudan University · Soongsil University
Day: ?? . Time: ?? SGT
Beyond XNU: Agentic Hunting for Vulnerabilities in TXM
Stefan EsserCalif
Day: ?? . Time: ?? SGT
No Time to Pwn2Own: Exploiting After the Draw
Evangelos Daravigkas , Ben KooTeam DDOS
Day: ?? . Time: ?? SGT
The Singularity Doesn't Care About Leaking Your Data From Prompt Injection to Posthuman Recon: A Field Report on Attacking AI in 2026
Markus VervierPersistent Security, X41 D-Sec GmbH
Day: ?? . Time: ?? SGT
Rooting the Google Pixel 10 with old-school techniques
Wang Yong-
Day: ?? . Time: ?? SGT
From 1-day vulnerability analysis to Copy Fail: Combining AI with Human Insight
Taeyang LeeTheori
Day: ?? . Time: ?? SGT
Capture Once, Hunt Forever: Building the Evidence Box Behind Cyborg Vulnerability Research
Luat NguyenCyberJutsu Academy
Day: ?? . Time: ?? SGT
Splitting the AI Brain: Discovering V8 Sandbox Bypasses with Multi-Agent Collaboration
PicassoDawn Security Lab, JD.com
??
A Year of Hacking with LLMs: A Practitioner's Reflections
// Abstract
Over the past year, the rapid advancement of large language models has fundamentally transformed offensive cybersecurity research. As a traditional security researcher with less AI background, I found myself increasingly relying on LLMs across multiple real-world offensive projects — and genuinely stunned by how fast the landscape is shifting.
In this keynote, I will walk through the technical architectures and hands-on lessons from several AI-augmented offensive security research projects I participated in over the past year. Beyond the technical details, I will share my observations on how AI is reshaping the offensive security industry, offer personal reflections on what this means for practitioners like us, and discuss how traditional security researchers can — and should — adapt to this new reality.
// Speakers
Dr. Edward Peng
Huazhong University of Science and Technology (HUST)
Dr. Zhiniang Peng (@edwardzpeng) is an associate professor at Huazhong University of Science and Technology (HUST). His current research areas include applied cryptography, software security and threat hunting. He has more than 20 years of experience in both offensive and defensive security and has published research in both academia and the industry.