Shumailov, Ilia

AI models collapse when trained on recursively generated data

Shumailov, I., Shumaylov, Z., Zhao, Y., Papernot, N., Anderson, R., & Gal, Y. (2024) · Nature

Topic ModelingEthics and Social Impacts of AI

Cited by 793

Scalable watermarking for identifying large language model outputs

Dathathri, S., See, A., Ghaisas, S., Huang, P.-S., McAdam, R., Welbl, J., Bachani, V., Kaskasoli, A., Stanforth, R., Matejovicova, T., et al. (2024) · Nature

Advanced Steganography and Watermarking TechniquesAdversarial Robustness in Machine Learning

Cited by 132

Sponge Examples: Energy-Latency Attacks on Neural Networks

Shumailov, I., Zhao, Y., Bates, D., Papernot, N., Mullins, R., & Anderson, R. (2021) · 2021 IEEE European Symposium on Security and Privacy (EuroS&P)

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 125

Bad Characters: Imperceptible NLP Attacks

Boucher, N., Shumailov, I., Anderson, R., & Papernot, N. (2022) · 2022 IEEE Symposium on Security and Privacy (SP)

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 102

On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

Thudi, A., Jia, H., Shumailov, I., & Papernot, N. (2021) · arXiv

Privacy-Preserving Technologies in DataEthics and Social Impacts of AI

Cited by 48

Defeating Prompt Injections by Design

Debenedetti, E., Shumailov, I., Fan, T., Hayes, J., Carlini, N., Fabian, D., Kern, C., Shi, C., Terzis, A., & Tramèr, F. (2026) · 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 15

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

Ghalebikesabi, S., Bagdasaryan, E., Yi, R., Yona, I., Shumailov, I., Pappu, A., Shi, C., Weidinger, L., Stanforth, R., Berrada, L., et al. (2024) · arXiv

Privacy, Security, and Data ProtectionPrivacy-Preserving Technologies in Data

Cited by 11

Open technical problems in open-weight ai model risk management

Casper, S., O'Brien, K., Longpre, S., Seger, E., Klyman, K., Bommasani, R., Nrusimha, A., Shumailov, I., Mindermann, S., Basart, S., et al. (2025) · SSRN Electronic Journal

Ethics and Social Impacts of AIAdversarial Robustness in Machine Learning

Cited by 3

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

Foerster, H., Blanchard, T., Nikolić, K., Shumailov, I., Zhang, C., Mullins, R., Papernot, N., Tramèr, F., & Zhao, Y. (2026) · arXiv

Security and Verification in ComputingAdversarial Robustness in Machine Learning

Cited by 0

Stealing Reasoning Traces from Proprietary LLM APIs

Panfilov, A., Schmotz, D., Shumailov, I., Beurer-Kellner, L., Schaeffer, J., Prabhu, A., Geiping, J., & Andriushchenko, M. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0