Our research seeks to empower individuals and organizations to control
how their data is used. We use techniques from cryptography,
programming languages, machine learning, operating systems, and other
areas to both understand and improve the privacy and security of
computing as practiced today, and as envisioned in the future. A major
current focus is on adversarial machine learning.
Orthodoxy means not thinking—not needing to think.
(George Orwell, 1984)
Uncovering Representation Vectors for LLM ‘Thought’ Control
Hannah Cyberey’s blog post summarizes our work on controlling the censorship imposed through refusal and thought suppression in model outputs.
Paper: Hannah Cyberey and David Evans. Steering the CensorShip: Uncovering Representation Vectors for LLM “Thought” Control. 23 April 2025.
Demos:
Code: https://github.com/hannahxchen/llm-censorship-steering
Now that I’ve testified as an Expert Witness on Privacy for the US (and 52 state partners), I can share some links about US v. Google. (I’ll wait until the judgement before sharing any of my own thoughts other than to say it was a great experience and a priviledge to be able to be part of this.)
The Department of Justice Website has public posts of many trial materials, including my demonstrative slides (with only one redaction).
This article has the most detailed and accurate account I’ve seen so far: Google Case Judge Weighs Rivals’ Data Needs Against Privacy [PDF]
The Docket (UVA Law News) has an article about the AI Law class I’m helping Tom Nachbar teach:
New Classes Explore Promise and Predicaments of Artificial Intelligence
Attorneys-in-Training Learn About Prompts, Policies and Governance
The Docket, 17 March 2025
Nachbar teamed up with David Evans, a professor of computer science at UVA, to teach the course, which, he said, is “a big part of what makes this class work.”
“This course takes a much more technical approach than typical law school courses do. We have the students actually going in, creating their own chatbots — they’re looking at the technology underlying generative AI,” Nachbar said. Better understanding how AI actually works, Nachbar said, is key in training lawyers to handle AI-related litigation in the future.
“I want my students to have a solid understanding about what’s actually happening under the hood, as it were, so that when they confront a case, they know what kinds of questions to start asking,” he said.
Full Article
Tom and I will co-teach a jointly-listed Law and Computer Science AI Law class in the fall.
I gave a short talk at an NSF workshop to spark research collaborations between researchers in Taiwan and the United States. My talk was about work Hannah Cyberey is leading on steering the internal representations of LLMs:
Steering around Censorship
Taiwan-US Cybersecurity Workshop
Arlington, Virginia
3 March 2025
I gave a short talk on explanability at the Virginia Journal of Social Policy and the Law Symposium on Artificial Intelligence at UVA Law School, 21 February 2025.
Can we explain AI model outputs? (PDF)
There’s an article about the event in the Virginia Law Weekly:
Law School Hosts LawTech Events, 26 February 2025.