About Me

Here is Aolin Ding. I am an AI Research Scientist Manager at Accenture’s Center for Advanced AI. I lead the security and evaluation team developing AI Refinery and its SDK — an industry AI multi-agent platform. My team was among the first worldwide to publish successful jailbreaks of large reasoning models (LRMs) in collaboration with university partners. Previously, I worked as a Research Associate Principal at Accenture Labs, focusing on AI safety, LLM security, PII protection, and privacy-preserving ML.

I obtained my Ph.D. in Electrical and Computer Engineering from Rutgers University in 2022 under the guidance of Prof. Saman Zonouz – who is now at Georgia Tech. I previously worked as a Research Intern at Accenture Labs and MERL for over a year. I received my B.E. degree in Electrical Engineering from UESTC in 2015.

• Email:

    $ echo YS5kaW5nQGFjY2VudHVyZS5jb20= | base64 --decode
  

Research Interests

• At Accenture, my research focuses on building secure, responsible and scalable multi-agent systems powered by LLMs. I specialize in agentic testing, evaluation, assessment and tooling of foundation model-based agents, with focus areas of safety, compliance, privacy, and security.

• In parallel, I actively advance my PhD research in the security of cyber-physical systems, industrial IoT, and embedded systems. In these domains, I leverage a combination of software analysis, physics-based monitoring, and machine learning approaches to develop innovative security solutions.

I have a solid record of publications and professional services at leading AI and security conferences and journals. Click here for my complete CV.