NU AI Safety

Resources

Below are some of the groups and individuals working on AI safety here at Northeastern.

Professors

  • Chenyan Jia, our faculty advisor, is an assistant professor of journalism with a joint appointment in Khoury. Jia's research sits where mass communication meets human-computer interaction, including human-centered AI, aligning AI with human values, and countering misinformation.
  • David Bau studies the structure and interpretation of deep networks, and leads the National Deep Inference Fabric. He has agreed to give guest talks. His lab also hosts open talks every Friday.
  • Weiyan Shi works on AI safety and holds two Open Philanthropy grants, on emergent misalignment and on evaluating the safety of AI agents.
  • Alina Oprea works on adversarial machine learning and trustworthy AI, and on security architectures for language model agents.
  • Malihe Alikhani works on AI ethics and is a visiting fellow at the Brookings Institution.
  • Sina Fazelpour, who holds a joint appointment in Khoury and philosophy, works on the ethics and governance of AI, including recent papers on disagreement in AI design, evaluation and alignment.

Organizations

  • NDIF is a national research computing platform for transparent, reproducible experiments on the largest open AI models. It is an NSF-funded project led by Professor Bau.
  • Northeastern is one of four universities in CRAIG, an NSF center on responsible AI and governance.
  • The Institute for Experiential AI counts responsible AI among its four research areas and runs a Responsible AI Practice.
  • The Ethics Institute has AI, information and data ethics as one of its main research areas.

Apart from Professor Jia, our faculty advisor, these researchers and organizations are not affiliated with NU AI Safety. We list them so that students can see the AI safety work already happening at Northeastern.