Concepedia

Ai Red-teaming

AI Red-Teaming is a systematic evaluative practice in artificial intelligence governance wherein adversarial testing methodologies are employed to proactively identify, analyze, and mitigate potential safety, security, and ethical risks in AI systems prior to deployment.

34

Publications

1.1K

Citations

185

Authors

23

Institutions

Publications per year

2017–2026

23

Variants

Ai Red Teaming

Parents

Publications

34

Red Teaming Language Models with Language Models

Ethan Perez, Saffron Huang, Francis Song et al. · 2022 · 258 citations · Full text

, , +9

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Deep Ganguli, Liane Lovitt, Jackson Kernion et al. · arXiv (Cornell University) · 2022 · 106 citations · Full text

, , +11

Jailbroken: How Does LLM Safety Training Fail?

Alexander Wei, Nika Haghtalab, Jacob Steinhardt · arXiv (Cornell University) · 2023 · 68 citations · Full text

, , +10

Computational Red Teaming: Past, Present and Future

Hussein A. Abbass, Axel Bender, Svetoslav Gaidow et al. · IEEE Computational Intelligence Magazine · 2011 · 62 citations

, , +17

Red-Teaming for Generative AI: Silver Bullet or Security Theater?

Michael Feffer, Anusha Sinha, Wesley Hanwen Deng et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · 2024 · 57 citations · Full text

, , +15

1–5 of 34

Authors

185

  1. CS
    Chwee Seng Choo

    DSO National Laboratories, Singapore

    6 publications · 91 citations

    6

    h-index

  2. HA
    Hussein A. Abbass

    UNSW Sydney, Australia

    4 publications · 119 citations

    4

    h-index

  3. PH
    Peter Henderson

    Butler University, United States

    2 publications · 60 citations

    3

    h-index

  4. EP
    Ethan Perez

    Rice University, United States

    3 publications · 382 citations

    3

    h-index

  5. CL
    Ching Lian Chua

    DSO National Laboratories, Singapore

    3 publications · 53 citations

    3

    h-index

1–5 of 185

Institutions

23

  1. DSO National Laboratories

    Singapore, Singapore

    6 h-index

    9 publications

    144 citations

  2. UNSW Sydney

    Sydney, Australia

    4 h-index

    7 publications

    161 citations

  3. Nanyang Technological University

    Singapore, Singapore

    3 h-index

    9 publications

    112 citations

  4. Defence Science and Technology Agency

    Singapore, Singapore

    3 h-index

    3 publications

    53 citations

  5. Carnegie Mellon University

    Pittsburgh, United States

    2 h-index

    5 publications

    285 citations

  6. Defence Science and Technology Group

    Canberra, Australia

    2 h-index

    4 publications

    202 citations

  7. Australian Defence Force Academy

    Canberra, Australia

    2 h-index

    4 publications

    113 citations

  8. University of Canberra

    Canberra, Australia

    2 h-index

    4 publications

    64 citations

1–8 of 23

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 358 citations

    11

    h-index

  2. SSRN Electronic Journal

    Repository · 2 publications · 37 citations

    2

    h-index

  3. Winter Simulation Conference

    Conference · 2 publications · 26 citations

    2

    h-index

  4. 1

    h-index

  5. IEEE Transactions on Dependable and Secure Computing

    TDSC · 1 publications · 29 citations

    1

    h-index

1–5