Selected Publications
- Longpre et al. “In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI.” Under review at ICML (2025).
- R.S. Portnoff. “Performance: Improving Quality while Mitigating Risks with Tests and Verification Procedures.” Technically Optimistic – Emerson Collective Substack (2025).
- Thorn and WeProtect. “Evolving Technologies Horizon Scan: A review of technologies carrying notable risk and opportunity in the fight against technology-facilitated child sexual exploitation.” Thorn Repository (2024). (Authors: M.Stroebel, R.S.Portnoff, C.Neiswender, S.Hingorani, I.Drennan)
- Thorn. “Mitigating the risk of generative AI models creating Child Sexual Abuse Materials: An analysis by child safety nonprofit Thorn.” Partnership on AI Repository (2024). (Authors: R.S.Portnoff and M.Stroebel)
- Thorn and ATIH. “Safety by Design for Generative AI: Preventing Child Sexual Abuse.” Thorn Repository (2024). (Authors: R.S.Portnoff et al.)
- D. Thiel, M.Stroebel, R.S.Portnoff. “Generative ML and CSAM: Implications and Mitigations.” Stanford Digital Repository (2023).
- R.S. Portnoff. “The Dark Net: De-Anonymization, Classification and Analysis.” UC Berkeley Technical Report (2017).
- R.S.Portnoff, D.Y. Huang, P. Doerfler, S. Afoz, D. McCoy. “Backpage and Bitcoin: Uncovering Human Traffickers.” KDD (2017)
- R.S.Portnoff, S. Afroz, G. Durrett, J.K.Kummerfeld, T. Berg-Kirkpatrick, D. McCoy, K. Levchencko, V. Paxson. “Tools for Automated Analysis of Cybercriminal Markets.” WWW (2017)
- R.S. Portnoff, L. Lee, S. Egelman, P. Mishra, D. T. Leung, D. Wagner. “Somebody’s Watching Me? Assessing The Effectiveness of Webcam Indicator Lights.” ACM CHI (2015).
- C. Dwork and R. Pottenger. “Toward Practicing Privacy.” Journal of the American Medical Informatics Association (2013)
Selected Blog Posts Referencing Dr. Portnoff’s Work
- Introducing Safer Predict: Using the Power of AI to Detect Child Sexual Abuse and Exploitation Online (Thorn, 2024)
- How Thorn Helps Investigators Find Children Faster (Thorn, 2024)
- Thorn and All Tech is Human Forge Generative AI Principles with AI Principles with AI Leaders to Enact Strong Child Safety Commitments (Thorn, 2024)
- Thorn and Griffeye Empower Global Law Enforcement to More Quickly Identify Abuse Victims (Thorn, 2024)
- How Hashing and Matching Can Help Prevent Revictimization (Thorn, 2023)
- How Thorn’s classifiers use artificial intelligence to build a safer internet (Thorn, 2023)
- New Technology to Help Companies Keep Young People Safe (Tech Coalition, 2023)
- Thorn’s CSAM Image Classifier Now Integrated With Magnet AXIOM (Magnet Forensics, 2023)
Selected References/Acknowledgements
- Was an AI Image Generator Taken Down for Making Child Sexual Abuse Material? (IEEE Spectrum, 2024)
- Dual-Use Foundation Models with Widely Available Model Weights (NTIA, 2024)
- Risk Mitigation Strategies for the Open Foundation Model Value Chain (Partnership on AI, 2024)
- Tech Trends Position Statement – Generative AI (eSafetyCommisioner, 2023)
Dr. Rebecca Portnoff 