Matthew Jagielski
- Scalable Extraction of Training Data from (Production) Language Models
2023/11/28 by Milad Nasr, Nasr, Milad, Nicholas Carlini +17 · 21 voices · 66 citations
Computer Science · #Adversarial Robustness in Machine Learning #Topic Modeling #Explainable Artificial Intelligence (XAI)
- Extracting Training Data from Diffusion Models
2023/01/30 by Nicholas Carlini, Jamie Hayes, Carlini, Nicholas +15 · 9 voices · 101 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis
- Poisoning Web-Scale Training Datasets is Practical
2023/02/20 by Nicholas Carlini, Carlini, Nicholas, Matthew Jagielski +16 · 6 voices · 46 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #COVID-19 diagnosis using AI #Topic Modeling #cs.CR #cs.LG
- Extracting Training Data from Large Language Models
2020/12/14 by Nicholas Carlini, Carlini, Nicholas, Florian Tramer +25 · 8 voices · 236 citations
Computer Science · #Adversarial Robustness in Machine Learning #Privacy-Preserving Technologies in Data #Topic Modeling #cs.CL #cs.CR #cs.LG
- Stealing Part of a Production Language Model
2024/03/11 by Nicholas Carlini, Carlini, Nicholas, Daniel Paleka +26 · 11 voices · 26 citations
Computer Science · #Natural Language Processing Techniques #cs.CR
- Quantifying Memorization Across Neural Language Models
2022/02/15 by Nicholas Carlini, Daphne Ippolito, Carlini, Nicholas +9 · 71 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
- PaLM 2 Technical Report
2023/05/17 by Rohan Anil, Andrew M. Dai, Anil, Rohan +224 · 68 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Auditing Differentially Private Machine Learning: How Private is Private SGD?
2020/06/13 by Matthew Jagielski, Jagielski, Matthew, Jonathan Ullman +3 · 28 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
2018/04/01 by Matthew Jagielski, Jagielski, Matthew, Alina Oprea +9 · 15 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Science and Game Theory (cs.GT) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
2024/12/09 by A. Feder Cooper, Cooper, A. Feder, Christopher A. Choquette-Choo +75 · 5 voices · 8 citations
Computer Science · Social Sciences · #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #cs.AI #cs.CY #cs.LG
- The Privacy Onion Effect: Memorization is Relative
2022/06/21 by Nicholas Carlini, Carlini, Nicholas, Matthew Jagielski +9 · 16 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- High Accuracy and High Fidelity Extraction of Neural Networks
2019/09/03 by Matthew Jagielski, Nicholas Carlini, Jagielski, Matthew +7 · 14 citations
Computer Science · #Adversarial Robustness in Machine Learning #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications
- Privacy Auditing with One (1) Training Run
2023/05/15 by Thomas Steinke, Milad Nasr, Steinke, Thomas +3 · 16 citations
Computer Science · Mathematics · #Privacy-Preserving Technologies in Data #Statistical Methods and Inference #Stochastic Gradient Optimization Techniques
- Counterfactual Memorization in Neural Language Models
2021/12/24 by Chiyuan Zhang, Zhang, Chiyuan, Daphne Ippolito +9 · 12 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
- Measuring Forgetting of Memorized Training Examples
2022/06/30 by Matthew Jagielski, Om Thakkar, Jagielski, Matthew +19 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Topic Modeling
- Differentially Private Fair Learning
2018/12/06 by Matthew Jagielski, Jagielski, Matthew, Michael Kearns +11 · 6 citations
Computer Science · Social Sciences · Mathematics · #Privacy-Preserving Technologies in Data #Ethics and Social Impacts of AI #Advanced Causal Inference Techniques
- On Evaluating the Durability of Safeguards for Open-Weight LLMs
2024/12/10 by Xiangyu Qi, Boyi Wei, Qi, Xiangyu +17 · 2 voices · 7 citations
Computer Science · #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #cs.AI #cs.CR
- UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
2024/06/27 by Ilia Shumailov, Shumailov, Ilia, Jamie Hayes +15 · 6 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Topic Modeling
- Debugging Differential Privacy: A Case Study for Privacy Auditing
2022/02/24 by Florian Tramèr, Tramer, Florian, Andreas Terzis +9 · 3 citations
Computer Science · #Privacy-Preserving Technologies in Data #Cryptography and Data Security #Stochastic Gradient Optimization Techniques
- Privacy Side Channels in Machine Learning Systems
2023/09/11 by Edoardo Debenedetti, Giorgio Severi, Debenedetti, Edoardo +13 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- CryptanalysisBench: Can LLMs do Cryptanalysis?
2026/07/20 by Lukas Fluri, Avital Shafran, Nicholas Carlini +5 · 3 voices
Computer Science · #cs.CR
- Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
2025/02/21 by Jaydeep Borkar, Borkar, Jaydeep, Matthew Jagielski +9 · 3 voices · 5 citations
#cs.CL #cs.CR
- Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
2023/04/14 by Rachel Cummings, Damien Desfontaines, Cummings, Rachel +45 · 3 citations
Social Sciences · #Privacy, Security, and Data Protection
- Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
2023/05/10 by Aldo Gael Carranza, Rezsa Farahani, Carranza, Aldo Gael +9 · 3 citations
Computer Science · #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Privacy-Preserving Technologies in Data
- Students Parrot Their Teachers: Membership Inference on Model Distillation
2023/03/06 by Matthew Jagielski, Jagielski, Matthew, Milad Nasr +7 · 1 voice · 2 citations
#cs.CR #cs.LG
- SNAP: Efficient Extraction of Private Properties with Poisoning
2022/08/25 by Harsh Chaudhari, Chaudhari, Harsh, John Abascal +9 · 2 citations
Computer Science · Medicine · #Privacy-Preserving Technologies in Data #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education
- Exploring the limits of strong membership inference attacks on large language models
2025/05/24 by Jamie Hayes, Ilia Shumailov, Hayes, Jamie +29 · 2 voices · 4 citations
Computer Science · #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling #cs.AI #cs.CR #cs.LG
- The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
2024/10/08 by Thomas Steinke, Milad Nasr, Steinke, Thomas +17 · 2 citations
Business, Management and Accounting · Decision Sciences · Economics, Econometrics and Finance · #Auction Theory and Applications #Cryptography and Security (cs.CR) #Digital Platforms and Economics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Merger and Competition Analysis
- Extracting alignment data in open models
2025/10/21 by Federico Barbero, Xiangming Gu, Barbero, Federico +15 · 1 voice
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Testing and Debugging Techniques #Topic Modeling
- Cascading Adversarial Bias from Injection to Distillation in Language Models
2025/05/30 by Harsh Chaudhari, Chaudhari, Harsh, Jamie Hayes +9 · 2 voices · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling #cs.CR #cs.LG