Blog icon

Dr Kristen Moore

Team Leader

https://people.csiro.au/m/k/kristen-moore

Biography

Dr Kristen Moore is a Principal Research Scientist at CSIRO and leads the Human-Centric Security team within the Technology Research Unit. Her research sits at the intersection of artificial intelligence and cybersecurity, spanning the security of AI systems, AI for cyber defence, and human–AI collaboration.

A major focus of her work is the challenge that generative AI poses to identity and trust. She studies deepfakes, scams and other forms of AI-enabled deception from both technical and human-centred perspectives: how they are created and detected, how they affect trust and decision-making, and how people can be better supported to recognise and respond to them. This includes research on deepfake and scam detection, safeguards against AI misuse, AI literacy, risk communication and interventions for online harms.

Kristen also works on the security and responsible use of agentic AI, including how increasingly autonomous systems may be attacked or misused, how they can be made more reliable and secure, and how they can support cybersecurity teams while maintaining effective human oversight. More broadly, she is interested in human–AI teaming and in designing AI-enabled cyber tools that are technically effective, operationally useful and understandable to the people who rely on them.

Before joining CSIRO, Kristen completed a PhD in mathematics at the Max Planck Institute for Gravitational Physics and the Free University of Berlin. She subsequently held postdoctoral positions at the University of California, Berkeley and Stanford University, before moving into industry roles at Gro Intelligence and Telstra.

Since joining CSIRO in 2020, Kristen has led major research programs in AI-enabled cyber defence and deception technologies. She is the lead inventor on a US patent, has received multiple AIIA iAwards, and has published in leading AI and cybersecurity venues including ICLR, ICML, EMNLP, IEEE Symposium on Security and Privacy, USENIX Security, EuroS&P, ACSAC and AsiaCCS.

Other Interests

Selected Publications:

  1. Haodong Lu, Chongyang Zhao, Jason Xue, Lina Yao, Kristen Moore, Dong Gong
    "Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts." Accepted to ICML 2026 Forty-third International Conference on Machine Learning. 2026. (CORE A*).

  2. Diksha Goel, Kristen Moore, Jeff Wang, Minjune Kim, Thanh Thi Nguyen. "Unveiling the black box: A multi-layer framework for explaining reinforcement learning-based cyber agents". Accepted at Journal of Information Security and Applications.

  3. Falih G. Febrinanto, Kristen Moore, Chandra Thapa, Jiangang Ma, Vidya Saikrishna. "SIGNL: A label-efficient audio deepfake detection system via spectral-temporal graph non-contrastive learning". Expert Systems with Applications. (2026).

  4. Kristen Moore, Diksha Goel, Cody James Christopher, Zhen Wang, Minjune Kim, Ahmed Ibrahim, Ahmad Mohsin, Seyit Camtepe. "TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulation". 2025 IEEE Annual Computer Security Applications Conference (ACSAC). (CORE A).

  5. Derui Wang, Kristen Moore, Diksha Goel, and Minjune Kim, CSIRO's Data61 and Cyber Security Cooperative Research Centre; Gang Li, Yang Li, and Robin Doss. "CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization". 34th USENIX Security Symposium (USENIX Security 25). (CORE A*).

  6. Minjune Kim, Jeff Wang, Kristen Moore, Diksha Goel, Derui Wang, Ahmad Mohsin, Ahmed Ibrahim, Robin Doss, Seyit Camtepe, Helge Janicke. "CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders". WWW '25: Companion Proceedings of the ACM on Web Conference 2025. (CORE A*).

  7. Fanzhen Liu, Sharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Jia Wu, Jian Yang, Quan Z Sheng. "Adversarial attacks against automated fact-checking: A survey". Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. (CORE A*).

  8. Falih Gozi Febrinanto, Kristen Moore, Chandra Thapa, Jiangang Ma, Vidya Saikrishna, Feng Xia. "Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection". Proc. Interspeech 2025. (CORE A).

  9. Binh M Le, Jiwon Kim, Shahroz Tariq, Kristen Moore, Alsharif Abuadbba, Simon S Woo. "Sok: Facial deepfake detectors." 2025 IEEE 10th European Symposium on Security and Privacy (EuroS&P). (CORE A).

  10. Diksha Goel, Kristen Moore, Mingyu Guo, Derui Wang, Minjune Kim & Seyit Camtepe. "Optimizing Cyber Defense in Dynamic Active Directories Through Reinforcement Learning". Computer Security – ESORICS 2024 (ESORICS). 2024. (CORE A).

  11. Haodong Lu and Dong Gong and Shuo Wang and Jason Xue and Lina Yao and Kristen Moore. "Learning with Mixture of Prototypes for Out-of-Distribution Detection". The Twelfth International Conference on Learning Representations (ICLR), 2024. (CORE A*).

  12. Kristen Moore, Shenjun Zhong, Zhen He, Torsten Rudolf, Nils Fisher, Brandon Victor, Neha Jindal. "A comprehensive solution to retrieval-based chatbot construction". Computer Speech & Language. (2024).

  13. Mousavi, Zahra, Chadni Islam, Kristen Moore, Alsharif Abuadbba, and Muhammad Ali Babar. "An Investigation into Misuse of Java Security APIs by Large Language Models." ACM ASIACCS (2024). (CORE A)

  14. Wang, Shuo, Alsharif Abuadbba, Sidharth Agarwal, Kristen Moore, Ruoxi Sun, Minhui Xue, Surya Nepal, Seyit Camtepe, and Salil Kanhere. "PublicCheck: Public Integrity Verification for Services of Run-time Deep Models." In 2023 IEEE Symposium on Security and Privacy (SP), pp. 1239-1256. IEEE Computer Society, 2023. (CORE A*)

  15. Park, Seonhye, Alsharif Abuadbba, Shuo Wang, Kristen Moore, Yansong Gao, Hyoungshick Kim, and Surya Nepal. "DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks." In Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC). 2023. (CORE A)

  16. Beomsang Cho, Binh M Le, Jiwon Kim, Simon Woo, Shahroz Tariq, Alsharif Abuadbba, Kristen Moore. "Towards Understanding of Deepfake Videos in the Wild". CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM). (CORE A).

  17. Kristen Moore, Cody James Christopher, David Liebowitz, Surya Nepal, Renee Selvey. "Modelling direct messaging networks with multiple recipients for cyber deception". 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P). (CORE A).

Academic Qualifications

  • 2012

    PhD Mathematics
    Max Planck Institute for Gravitational Physics & Freie Universität Berlin.

  • 2007

    BSc (Hons): Mathematics and Physics
    Monash University

Achievements and Awards

  • 2025-2025

    iAward Winner of Victorian "Government and Public Service" category
    AIIA

  • 2025-2025

    Outstanding PC Award for AsiaCCS 2025
    AsiaCCS 2025

  • 2023-2026

    Julius Career Award CSIRO
    CSIRO

  • 2024-2024

    Finalist for Australian AI Awards 2024 - AI Female Leader of the Year (Enterprise)
    Momentum Media

  • 2023-2023

    Merit Award for "Technology Platform" category at ACT iAwards
    AIIA

  • 2022-2022

    Finalist for Women In AI (WAI) Australia/NZ award in Cyber Security
    Women in AI

  • 2021-2021

    Women in Science Award
    CSIRO (SCS, Data61)

Current Roles

  • Group Leader (Acting)
    Cybersecurity & Quantum Systems

Community and Corporate Citizenship

  • 2025-2026

    TPC/Reviewer: ICLR 2025, 2026

  • 2025-2026

    TPC/Reviewer: AsiaCCS 2025, 2026

  • 2026-2026

    TPC/Reviewer: EuroS&P 2026

Professional Areas

Publications