Daniel Kang

我的研究主要分为两个方向。

安全：

我希望通过实际演示，证明现实中的 AI 部署存在安全漏洞，推动企业投入资源，采用能够解决根本安全问题的对齐技术。

验证：

通过可信执行环境（TEE）或零知识证明（ZKP）进行验证。

申请

View all streams

研究小组概览

安全方向：

通过攻击现实中的 AI 部署，展示其安全漏洞。

验证方向：可信执行环境（TEE）或零知识证明（ZKP）。

导师指导方式：

Light-touch (.5 hours of weekly 1:1s)

项目期间的工作地点：

SF Bay Area

伦敦办公偏好：

Indifferent

伯克利办公偏好：

Strong preference

导师

Daniel Kang

University of Illinois Urbana-Champaign

教授

Biosecurity

Capability and Propensity Evaluations

AI 系统安全

AI 技术治理

对抗鲁棒性与安全防护

Daniel is a professor of computer science at UIUC, where he studies the progress of AI, with a particular focus on dangerous capabilities of AI agents. His work includes:

- CVE-Bench, an award winning benchmark (SafeBench award, ICML spotlight) that is used by frontier labs and governments to measure AI agents' ability to find and exploit real-world vulnerabilities.

- Agent Benchmark Checklist, an award winning work (Berkeley AI summit, 1st place Benchmarks & Evaluations track) that highlights major issues in existing benchmarks.

- InjecAgent, one of the first AI agent safety benchmarks, used by governments and major labs.

我们希望招收的学员

For security:

You should have a strong security mindset, having demonstrated the willingness to be creative on this. I would like to see past demonstration of willingness to get your hands dirty and try many different systems.

For benchmarks:

As creative as possible, willingness to work on the nitty gritty, willingness to work really hard on problems other people find boring. Interests as far away from SF-related interests as possible.

有可信执行环境（TEE）或零知识证明（ZKP）方面的经验。

项目遴选

导师会与学员讨论项目想法。