Matthew Jagielski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Matthew Jagielski has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Chiyuan Zhang
2 shared publications- Daphne Ippolito
University of Pennsylvania
2 shared publications - Florian Tramèr
ETH Zurich, Zurich, Switzerland
2 shared publications - Katherine Lee
The GenLaw Center, San Francisco, CA, USA, Cornell University, Ithaca, NY, USA
2 shared publications Nicholas Carlini
2 shared publicationsAbhradeep Thakurta
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7507-7509
AISec '26: 19th Workshop on Artificial Intelligence and Security
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7507-7509
Open AccessAISec '26: 19th Workshop on Artificial Intelligence and Security
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4889-4891
AISec '25: 18th ACM Workshop on Artificial Intelligence and Security
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4889-4891
Open AccessAISec '25: 18th ACM Workshop on Artificial Intelligence and Security
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4409-4422
Cascading Adversarial Bias from Injection to Distillation in Language Models
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4409-4422
Open AccessCascading Adversarial Bias from Injection to Distillation in Language Models
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4905-4906
AISec '24: 17th ACM Workshop on Artificial Intelligence and Security
The use of Artificial Intelligence (AI) and Machine Learning (ML) has been the center of the most outstanding advancements in the last years. The ability to analyze considerable streams of data in real time makes these technologies the most promising tool in many domains, including cybersecurity. As an outstanding example, ML can be used for identifying malware because of its ability to detect patterns otherwise difficult to see for humans and hard-coded rules. However, the use of AI and ML in security-relevant domains raised rightful concerns about their trustworthiness and robustness, espe- cially in front of adaptive attackers. Additionally, privacy threats are now emerging as a crucial aspect and need proper testing and possibly mitigation to prevent data stealing and leakage of sensitive information. AISec provides a venue for presenting and discussing new developments in the intersection of security and privacy with AI and ML. The AISec'24 workshop proceedings are available at: https://dl.acm.org/doi/proceedings/10.1145/3658644.3691545.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4905-4906
Open AccessAISec '24: 17th ACM Workshop on Artificial Intelligence and Security
The use of Artificial Intelligence (AI) and Machine Learning (ML) has been the center of the most outstanding advancements in the last years. The ability to analyze considerable streams of data in real time makes these technologies the most promising tool in many domains, including cybersecurity. As an outstanding example, ML can be used for identifying malware because of its ability to detect patterns otherwise difficult to see for humans and hard-coded rules. However, the use of AI and ML in security-relevant domains raised rightful concerns about their trustworthiness and robustness, espe- cially in front of adaptive attackers. Additionally, privacy threats are now emerging as a crucial aspect and need proper testing and possibly mitigation to prevent data stealing and leakage of sensitive information. AISec provides a venue for presenting and discussing new developments in the intersection of security and privacy with AI and ML. The AISec'24 workshop proceedings are available at: https://dl.acm.org/doi/proceedings/10.1145/3658644.3691545.
- Open Access
Measuring Forgetting of Memorized Training Examples
Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In forgetting, examples which appeared early in training are forgotten by the end. In this work, we connect these phenomena. We propose a technique to measure to what extent models "forget" the specifics of training examples, becoming less susceptible to privacy attacks on examples they have not seen recently. We show that, while non-convex models can memorize data forever in the worst-case, standard image, speech, and language models empirically do forget examples over time. We identify nondeterminism as a potential explanation, showing that deterministically trained models do not forget. Our results suggest that examples seen early when training with extremely large datasets - for instance those examples used to pre-train a model - may observe privacy benefits at the expense of examples seen later.
Open AccessMeasuring Forgetting of Memorized Training Examples
Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In forgetting, examples which appeared early in training are forgotten by the end. In this work, we connect these phenomena. We propose a technique to measure to what extent models "forget" the specifics of training examples, becoming less susceptible to privacy attacks on examples they have not seen recently. We show that, while non-convex models can memorize data forever in the worst-case, standard image, speech, and language models empirically do forget examples over time. We identify nondeterminism as a potential explanation, showing that deterministically trained models do not forget. Our results suggest that examples seen early when training with extremely large datasets - for instance those examples used to pre-train a model - may observe privacy benefits at the expense of examples seen later.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 28-53
Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy
Daphne Ippolito, Florian Tramer, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher Choquette Choo, Nicholas Carlini. Proceedings of the 16th International Natural Language Generation Conference. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 28-53
Top Cited PapersOpen AccessPreventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy
Daphne Ippolito, Florian Tramer, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher Choquette Choo, Nicholas Carlini. Proceedings of the 16th International Natural Language Generation Conference. 2023.
- Open Access
- 24 August 2022
- Published by Northeastern University Library
Integrity and privacy in adversarial machine learning
- 24 August 2022
- Published by Northeastern University Library
Open AccessIntegrity and privacy in adversarial machine learning