DEFCON 31
Talks
| Day | Start Time | Length (Minutes) | Primary Speaker | Talk Title |
|---|---|---|---|---|
| Friday | 10:00 | 10 | AI Village Organizers | AI Village Opening Remarks |
| Friday | 10:15 | 45 | Joshua Saxe, META | Keynote: The last attempted AI revolution in security, and the next one (Slides on Google Drive) |
| Friday | 11:00 | 15 | Will Pearce | CTF Kickoff and Introduction |
| Friday | 11:30 | 25 | Kyle Easterly; Mitch Kitter | LLMs: Loose Lips Multipliers |
| Friday | 12:00 | 25 | Adhishree Kathikar; Aishwarya Nair | Assessing the Vulnerabilities of the Open-Source Artificial Intelligence (AI) Landscape: A Large-Scale Analysis of the Hugging Face Platform (Slides) |
| Friday | 12:30 | 55 | Marta Janus | Not Just The Pickle: An Overview of Exploitable ML Serialization Formats |
| Friday | 13:30 | 25 | Ari Herbert-Voss; Shane Caldwell | How NOT to Train your Hack Bot: Dos and Don’ts of Building Offensive GPTs |
| Friday | 14:00 | 55 | Ram Shankar Siva Kumar | A Few Useful Lessons about AI Red Teaming |
| Friday | 16:00 | 55 | Chloe Messdaghi moderating | Panel: Unveiling the Secrets: Breaking into AI/ML Security Bug Bounty Hunting |
| Friday | 17:00 | 55 | Tom Bonner | Ghost in the Neurons - ML Webshells |
| Day | Start Time | Length (Minutes) | Primary Speaker | Talk Title |
|---|---|---|---|---|
| Saturday | 10:30 | 55 | Mikel Rodriguez; Daniel Fabian; Sarah Hodkinson | Keynote 2: AI red teaming tradecraft: a team of teams approach (Slides) |
| Saturday | 11:30 | 55 | Eryk Salvaggio moderating | Panel : Creative Misuse of AI Systems |
| Saturday | 12:30 | 55 | Robert Hudock; Nick Maietta | LLM Legal Risk Management, and Use Case Development Strategies to Minimize Risk (Slides) |
| Saturday | 13:30 | 55 | Ben Gelman; Younghoo Lee | The Sinister Synergy of Advanced AI: Automatically Orchestrating Large-scale Scam Campaigns with Large Generative Models (Slides) |
| Saturday | 15:00 | 25 | Adrian Wood | you sound confused, anyways - thanks for the jewels. (Slides) |
| Saturday | 15:30 | 25 | Kenneth Yeung | Hackaprompt 2023: Trials and Tribulations (Slides) |
| Saturday | 16:00 | 25 | Ram Shankar Siva Kumar | Ignore the Law: The Legal Risks of Prompt Injection Attacks on Large Language Models |
| Saturday | 16:30 | 55 | Gavin Klondike | ChatGPT: Your Red Teaming Ally |
| Day | Start Time | Length (Minutes) | Primary Speaker | Talk Title |
|---|---|---|---|---|
| Sunday | 10:00 | 25 | Rafael Turner, Dedrone | Fuzzing and Symbolic Execution: Offensive Techniques to Unmask Vulnerabilities in Neural Networks |
| Sunday | 10:45 | 45 | Sven Cattell | GRT Report Out |
| Sunday | 11:15 | 30 | AI Village Organizers | AI Village Closing Remarks |
Demos
Last year we hosted StableDiffusion a few days before it’s release. This year we are returning with more demo stations and opening them to submissions! We will have 2 demo stations equipped with a pair of A6000, and a demo station for remote demos. We’ll be hosting ControlNet, Whisper, Alpaca, and notebooks that get into the gory details of these models.
If you want to present an open source demo that you think the security community should see, please get in touch!
Prompt Detective
Are you curious about the capabilities and limitations of large language models (LLMs) like GPT3 and Bloom? Do you want to participate in a unique exercise where you try to get LLMs to misbehave? Join us for Prompt Detective where you’ll learn about the technology behind LLMs, their applications, and their current limitations. We will have a few target LLMs set up where you can learn how to perform prompt injection against different levels of RLHF. This workshop is open to all individuals, regardless of their background or expertise. It is designed to teach prompt engineering techniques to beginners, and provide a safe target range for people to practice the basics of manipulating the egde cases of this new technology in potentially harmful ways.