Jamie Hayes - RankMe

86 papers A* 16A 2Journal 59Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Estimating near-verbatim extraction risk in language models with decoding-constrained beam search. CoRR A. Feder Cooper, Mark A. Lemley, Christopher De Sa, Lea Duesterwald, Allison Casasola, Jamie Hayes, Katherine Lee, Daniel E. Ho, Percy Liang
2026	J	`jnl`	Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models. CoRR Harsh Chaudhari, Ethan Rathbun, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea
2025	J	`jnl`	(ϵ, δ) Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees. CoRR Juan Felipe Gómez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela
2025	J	`jnl`	Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries. CoRR Marika Swanberg, Meenatchi Sundaram Muthu Selva Annamalai, Jamie Hayes, Borja Balle, Adam D. Smith
2025	A*	`conf`	Cascading Adversarial Bias from Injection to Distillation in Language Models. CCS Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea
2025	J	`jnl`	Cascading Adversarial Bias from Injection to Distillation in Language Models. CoRR Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea
2025	J	`jnl`	Defeating Prompt Injections by Design. CoRR Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan, Jamie Hayes, Nicholas Carlini, Daniel Fabian, Christoph Kern, Chongyang Shi, Andreas Terzis, Florian Tramèr
2025	J	`jnl`	Extracting alignment data in open models. CoRR Federico Barbero, Xiangming Gu, Christopher A. Choquette-Choo, Chawin Sitawarin, Matthew Jagielski, Itay Yona, Petar Velickovic, Ilia Shumailov, Jamie Hayes
2025	—	`conf`	Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy. SaTML Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa, Nicolas Papernot
2025	A*	`conf`	Interpreting the Repeated Token Phenomenon in Large Language Models. ICML Itay Yona, Ilia Shumailov, Jamie Hayes, Yossi Gandelsman
2025	J	`jnl`	Interpreting the Repeated Token Phenomenon in Large Language Models. CoRR Itay Yona, Ilia Shumailov, Jamie Hayes, Federico Barbero, Yossi Gandelsman
2025	J	`jnl`	Large Language Models Can Verbatim Reproduce Long Malicious Sequences. CoRR Sharon Lin, Krishnamurthy Dvijotham, Jamie Hayes, Chongyang Shi, Ilia Shumailov, Shuang Song
2025	J	`jnl`	Lessons from Defending Gemini Against Indirect Prompt Injections. CoRR Chongyang Shi, Sharon Lin, Shuang Song, Jamie Hayes, Ilia Shumailov, Itay Yona, Juliette Pluto, Aneesh Pappu, Christopher A. Choquette-Choo, Milad Nasr, Chawin Sitawarin, Gena Gibson, Andreas Terzis, John Flynn
2025	—	`conf`	Locking Machine Learning Models into Hardware. SaTML Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
2025	A*	`conf`	Measuring memorization in RLHF for code completion. ICLR Jamie Hayes, Ilia Shumailov, William P. Porter, Aneesh Pappu
2025	—	`conf`	Measuring memorization in language models via probabilistic extraction. NAACL (Long Papers) Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona, Ilia Shumailov, Milad Nasr, Christopher A. Choquette-Choo, Katherine Lee, A. Feder Cooper
2025	J	`jnl`	Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated. CoRR Hanna Foerster, Ilia Shumailov, Yiren Zhao, Harsh Chaudhari, Jamie Hayes, Robert Mullins, Yarin Gal
2025	J	`jnl`	Soft Instruction De-escalation Defense. CoRR Nils Philipp Walter, Chawin Sitawarin, Jamie Hayes, David Stutz, Ilia Shumailov
2025	J	`jnl`	Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models. CoRR Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo, Matthew Jagielski, Georgios Kaissis, Katherine Lee, Milad Nasr, Sahra Ghalebikesabi, Niloofar Mireshghallah, Meenatchi Sundaram Mutu Selva Annamalai, Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye, Franziska Boenisch, Adam Dziedzic, A. Feder Cooper
2025	J	`jnl`	SynthID-Image: Image watermarking at internet scale. CoRR Sven Gowal, Rudy Bunel, Florian Stimberg, David Stutz, Guillermo Ortiz-Jiménez, Christina Kouridi, Mel Vecerík, Jamie Hayes, Sylvestre-Alvise Rebuffi, Paul Bernard, Chris Gamble, Miklós Z. Horváth, Fabian Kaczmarczyck, Alex Kaskasoli, Aleksandar Petrov, Ilia Shumailov, Meghana Thotakuri, Olivia Wiles, Jessica Yung, Zahra Ahmed, Victor Martin, Simon Rosen, Christopher Savcak, Armin Senoner, Nidhi Vyas, Pushmeet Kohli
2025	J	`jnl`	The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections. CoRR Milad Nasr, Nicholas Carlini, Chawin Sitawarin, Sander V. Schulhoff, Jamie Hayes, Michael Ilie, Juliette Pluto, Shuang Song, Harsh Chaudhari, Ilia Shumailov, Abhradeep Thakurta, Kai Yuanqing Xiao, Andreas Terzis, Florian Tramèr
2025	J	`jnl`	The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing. CoRR Meenatchi Sundaram Muthu Selva Annamalai, Borja Balle, Jamie Hayes, Georgios Kaissis, Emiliano De Cristofaro
2025	A*	`conf`	The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. ICLR Milad Nasr, Thomas Steinke, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2025	J	`jnl`	Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy. CoRR Bogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Jamie Hayes, Borja Balle, Flávio P. Calmon, Jean Louis Raisaro
2024	J	`jnl`	Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition. CoRR Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa, Jamie Hayes, Meghdad Kurmanji, Kairan Zhao, Vincent Dumoulin, Júlio C. S. Jacques Júnior, Ioannis Mitliagkas, Jun Wan, Lisheng Sun-Hosoya, Sergio Escalera, Gintare Karolina Dziugaite, Peter Triantafillou, Isabelle Guyon
2024	A*	`conf`	Beyond Slow Signs in High-fidelity Model Extraction. NeurIPS Hanna Foerster, Robert Mullins, Ilia Shumailov, Jamie Hayes
2024	J	`jnl`	Beyond Slow Signs in High-fidelity Model Extraction. CoRR Hanna Foerster, Robert Mullins, Ilia Shumailov, Jamie Hayes
2024	A*	`conf`	Beyond the Calibration Point: Mechanism Comparison in Differential Privacy. ICML Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert
2024	J	`jnl`	Beyond the Calibration Point: Mechanism Comparison in Differential Privacy. CoRR Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert
2024	J	`jnl`	Buffer Overflow in Mixture of Experts. CoRR Jamie Hayes, Ilia Shumailov, Itay Yona
2024	J	`jnl`	Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy. CoRR Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa, Nicolas Papernot
2024	J	`jnl`	Locking Machine Learning Models into Hardware. CoRR Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
2024	J	`jnl`	Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice. CoRR A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski, Katja Filippova, Ken Ziyu Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Niloofar Mireshghallah, Ilia Shumailov, Eleni Triantafillou, Peter Kairouz, Nicole Mitchell, Percy Liang, Daniel E. Ho, Yejin Choi, Sanmi Koyejo, Fernando A. Delgado, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Solon Barocas, Amy Cyphert, Mark A. Lemley, danah boyd, Jennifer Wortman Vaughan, Miles Brundage, David Bau, Seth Neel, Abigail Z. Jacobs, Andreas Terzis, Hanna M. Wallach, Nicolas Papernot, Katherine Lee
2024	J	`jnl`	Measuring memorization in RLHF for code completion. CoRR Aneesh Pappu, Billy Porter, Ilia Shumailov, Jamie Hayes
2024	J	`jnl`	Measuring memorization through probabilistic discoverable extraction. CoRR Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona, Ilia Shumailov
2024	J	`jnl`	Scalable watermarking for identifying large language model outputs. Nat. Sumanth Dathathri, Abigail See, Sumedh Ghaisas, Po-Sen Huang, Rob McAdam, Johannes Welbl, Vandana Bachani, Alex Kaskasoli, Robert Stanforth, Tatiana Matejovicova, Jamie Hayes, Nidhi Vyas, Majd Al Merey, Jonah Brown-Cohen, Rudy Bunel, Borja Balle, A. Taylan Cemgil, Zahra Ahmed, Kitty Stacpoole, Ilia Shumailov, Ciprian Baetu, Sven Gowal, Demis Hassabis, Pushmeet Kohli
2024	J	`jnl`	Stealing User Prompts from Mixture of Experts. CoRR Itay Yona, Ilia Shumailov, Jamie Hayes, Nicholas Carlini
2024	J	`jnl`	The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. CoRR Thomas Steinke, Milad Nasr, Arun Ganesh, Borja Balle, Christopher A. Choquette-Choo, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2024	J	`jnl`	To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling. CoRR Meenatchi Sundaram Muthu Selva Annamalai, Borja Balle, Emiliano De Cristofaro, Jamie Hayes
2024	J	`jnl`	UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI. CoRR Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jiménez, Nicolas Papernot, Matthew Jagielski, Itay Yona, Heidi Howard, Eugene Bagdasaryan
2023	A	`conf`	Adaptive Webpage Fingerprinting from TLS Traces. DSN Vasilios Mavroudis, Jamie Hayes
2023	J	`jnl`	Bounding Training Data Reconstruction in DP-SGD. CoRR Jamie Hayes, Saeed Mahloujifar, Borja Balle
2023	J	`jnl`	Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy. CoRR Georgios Kaissis, Jamie Hayes, Alexander Ziller, Daniel Rueckert
2023	A*	`conf`	Bounding training data reconstruction in DP-SGD. NeurIPS Jamie Hayes, Borja Balle, Saeed Mahloujifar
2023	J	`jnl`	Differentially Private Diffusion Models Generate Useful Synthetic Images. CoRR Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja Balle
2023	A*	`conf`	Extracting Training Data from Diffusion Models. USENIX Security Symposium Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace
2023	J	`jnl`	Extracting Training Data from Diffusion Models. CoRR Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace
2023	A	`conf`	Mnemonist: Locating Model Parameters that Memorize Training Examples. UAI Ali Shahin Shamsabadi, Jamie Hayes, Borja Balle, Adrian Weller
2023	A*	`conf`	Tight Auditing of Differentially Private Machine Learning. USENIX Security Symposium Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
2023	J	`jnl`	Tight Auditing of Differentially Private Machine Learning. CoRR Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
2023	A*	`conf`	Towards Unbounded Machine Unlearning. NeurIPS Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes, Eleni Triantafillou
2023	J	`jnl`	Unlocking Accuracy and Fairness in Differentially Private Image Classification. CoRR Leonard Berrada, Soham De, Judy Hanwen Shen, Jamie Hayes, Robert Stanforth, David Stutz, Pushmeet Kohli, Samuel L. Smith, Borja Balle
2022	J	`jnl`	Learning to be adversarially robust and differentially private. CoRR Jamie Hayes, Borja Balle, M. Pawan Kumar
2022	A*	`conf`	Local and Central Differential Privacy for Robustness and Privacy in Federated Learning. NDSS Mohammad Naseri, Jamie Hayes, Emiliano De Cristofaro
2022	A*	`conf`	Reconstructing Training Data with Informed Adversaries. SP Borja Balle, Giovanni Cherubin, Jamie Hayes
2022	J	`jnl`	Reconstructing Training Data with Informed Adversaries. CoRR Borja Balle, Giovanni Cherubin, Jamie Hayes
2022	J	`jnl`	Unlocking High-Accuracy Differentially Private Image Classification through Scale. CoRR Soham De, Leonard Berrada, Jamie Hayes, Samuel L. Smith, Borja Balle
2020	A*	`conf`	A Framework for robustness Certification of Smoothed Classifiers using F-Divergences. ICLR Krishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, J. Zico Kolter, Chongli Qin, András György, Kai Xiao, Sven Gowal, Pushmeet Kohli
2020	J	`jnl`	Adaptive Traffic Fingerprinting: Large-scale Inference under Realistic Assumptions. CoRR Vasilios Mavroudis, Jamie Hayes
2020	—	`conf`	Extensions and limitations of randomized smoothing for robustness guarantees. CVPR Workshops Jamie Hayes
2020	J	`jnl`	Extensions and limitations of randomized smoothing for robustness guarantees. CoRR Jamie Hayes
2020	J	`jnl`	Provable trade-offs between private & robust machine learning. CoRR Jamie Hayes
2020	J	`jnl`	Toward Robustness and Privacy in Federated Learning: Experimenting with Local and Central Differential Privacy. CoRR Mohammad Naseri, Jamie Hayes, Emiliano De Cristofaro
2020	J	`jnl`	Towards transformation-resilient provenance detection of digital media. CoRR Jamie Hayes, Krishnamurthy Dvijotham, Yutian Chen, Sander Dieleman, Pushmeet Kohli, Norman Casagrande
2020	J	`jnl`	Unique properties of adversarially trained linear classifiers on Gaussian data. CoRR Jamie Hayes
2019	J	`jnl`	Contamination Attacks and Mitigation in Multi-Party Machine Learning. CoRR Jamie Hayes, Olga Ohrimenko
2019	J	`jnl`	LOGAN: Membership Inference Attacks Against Generative Models. Proc. Priv. Enhancing Technol. Jamie Hayes, Luca Melis, George Danezis, Emiliano De Cristofaro
2018	J	`jnl`	A note on hyperparameters in black-box adversarial examples. CoRR Jamie Hayes
2018	A*	`conf`	Contamination Attacks and Mitigation in Multi-Party Machine Learning. NeurIPS Jamie Hayes, Olga Ohrimenko
2018	J	`jnl`	Evading classifiers in discrete domains with provable optimality guarantees. CoRR Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso
2018	—	`conf`	Learning Universal Adversarial Perturbations with Generative Models. IEEE Symposium on Security and Privacy Workshops Jamie Hayes, George Danezis
2018	—	`conf`	On Visible Adversarial Perturbations & Digital Watermarking. CVPR Workshops Jamie Hayes
2017	—	`conf`	AnNotify: A Private Notification Service. WPES@CCS Ania M. Piotrowska, Jamie Hayes, Nethanel Gelernter, George Danezis, Amir Herzberg
2017	—	`conf`	Generating steganographic images via adversarial training. NIPS Jamie Hayes, George Danezis
2017	J	`jnl`	LOGAN: Evaluating Privacy Leakage of Generative Models Using Generative Adversarial Networks. CoRR Jamie Hayes, Luca Melis, George Danezis, Emiliano De Cristofaro
2017	J	`jnl`	Machine Learning as an Adversarial Service: Learning Black-Box Adversarial Examples. CoRR Jamie Hayes, George Danezis
2017	A*	`conf`	The Loopix Anonymity System. USENIX Security Symposium Ania M. Piotrowska, Jamie Hayes, Tariq Elahi, Sebastian Meiser, George Danezis
2017	J	`jnl`	The Loopix Anonymity System. CoRR Ania M. Piotrowska, Jamie Hayes, Tariq Elahi, Sebastian Meiser, George Danezis
2017	J	`jnl`	Website Fingerprinting Defenses at the Application Layer. Proc. Priv. Enhancing Technol. Giovanni Cherubin, Jamie Hayes, Marc Juarez
2017	J	`jnl`	ste-GAN-ography: Generating Steganographic Images via Adversarial Training. CoRR Jamie Hayes, George Danezis
2016	J	`jnl`	AnoNotify: A Private Notification Service. IACR Cryptol. ePrint Arch. Ania M. Piotrowska, Jamie Hayes, Nethanel Gelernter, George Danezis, Amir Herzberg
2016	—	`conf`	TASP: Towards Anonymity Sets that Persist. WPES@CCS Jamie Hayes, Carmela Troncoso, George Danezis
2016	J	`jnl`	Traffic Confirmation Attacks Despite Noise. CoRR Jamie Hayes
2016	A*	`conf`	k-fingerprinting: A Robust Scalable Website Fingerprinting Technique. USENIX Security Symposium Jamie Hayes, George Danezis
2015	J	`jnl`	Better open-world website fingerprinting. CoRR Jamie Hayes, George Danezis
2015	J	`jnl`	Guard Sets for Onion Routing. Proc. Priv. Enhancing Technol. Jamie Hayes, George Danezis