Matthew Jagielski
Matthew Jagielski
Google DeepMind
Verified email at - Homepage
Cited by
Cited by
Extracting training data from large language models
N Carlini, F Tramer, E Wallace, M Jagielski, A Herbert-Voss, K Lee, ...
30th USENIX Security Symposium (USENIX Security 21), 2633-2650, 2021
PaLM 2 Technical Report
R Anil, AM Dai, O Firat, M Johnson, D Lepikhin, A Passos, S Shakeri, ...
arXiv preprint arXiv:2305.10403, 2023
Manipulating machine learning: Poisoning attacks and countermeasures for regression learning
M Jagielski, A Oprea, B Biggio, C Liu, C Nita-Rotaru, B Li
2018 IEEE Symposium on Security and Privacy (SP), 19-35, 2018
Quantifying Memorization Across Neural Language Models
N Carlini, D Ippolito, M Jagielski, K Lee, F Tramer, C Zhang
arXiv preprint arXiv:2202.07646, 2022
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks
A Demontis, M Melis, M Pintor, M Jagielski, B Biggio, A Oprea, ...
28th {USENIX} Security Symposium ({USENIX} Security 19), 321-338, 2019
High accuracy and high fidelity extraction of neural networks
M Jagielski, N Carlini, D Berthelot, A Kurakin, N Papernot
29th USENIX security symposium (USENIX Security 20), 1345-1362, 2020
Extracting training data from diffusion models
N Carlini, J Hayes, M Nasr, M Jagielski, V Sehwag, F Tramèr, B Balle, ...
arXiv preprint arXiv:2301.13188, 2023
Auditing differentially private machine learning: How private is private sgd?
M Jagielski, J Ullman, A Oprea
Advances in Neural Information Processing Systems 33, 22205-22216, 2020
Differentially private fair learning
M Jagielski, M Kearns, J Mao, A Oprea, A Roth, S Sharifi-Malvajerdi, ...
International Conference on Machine Learning, 3000-3008, 2019
Are aligned neural networks adversarially aligned?
N Carlini, M Nasr, CA Choquette-Choo, M Jagielski, I Gao, PWW Koh, ...
Advances in Neural Information Processing Systems 36, 2024
Cryptanalytic extraction of neural network models
N Carlini, M Jagielski, I Mironov
Advances in Cryptology–CRYPTO 2020: 40th Annual International Cryptology …, 2020
Scalable Extraction of Training Data from (Production) Language Models
M Nasr, N Carlini, J Hayase, M Jagielski, AF Cooper, D Ippolito, ...
arXiv preprint arXiv:2311.17035, 2023
Subpopulation data poisoning attacks
M Jagielski, G Severi, N Pousette Harger, A Oprea
Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications …, 2021
Poisoning Web-Scale Training Datasets is Practical
N Carlini, M Jagielski, CA Choquette-Choo, D Paleka, W Pearce, ...
arXiv preprint arXiv:2302.10149, 2023
Counterfactual memorization in neural language models
C Zhang, D Ippolito, K Lee, M Jagielski, F Tramèr, N Carlini
Advances in Neural Information Processing Systems 36, 39321-39362, 2023
Preventing generation of verbatim memorization in language models gives a false sense of privacy
D Ippolito, F Tramèr, M Nasr, C Zhang, M Jagielski, K Lee, ...
Proceedings of the 16th International Natural Language Generation Conference …, 2023
Truth serum: Poisoning machine learning models to reveal their secrets
F Tramèr, R Shokri, A San Joaquin, H Le, M Jagielski, S Hong, N Carlini
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications …, 2022
Measuring Forgetting of Memorized Training Examples
M Jagielski, O Thakkar, F Tramèr, D Ippolito, K Lee, N Carlini, E Wallace, ...
arXiv preprint arXiv:2207.00099, 2022
The privacy onion effect: Memorization is relative
N Carlini, M Jagielski, C Zhang, N Papernot, A Terzis, F Tramer
Advances in Neural Information Processing Systems 35, 13263-13276, 2022
Threat Detection for Collaborative Adaptive Cruise Control in Connected Cars
M Jagielski, N Jones, CW Lin, C Nita-Rotaru, S Shiraishi
Proceedings of the 11th ACM Conference on Security & Privacy in Wireless and …, 2018
The system can't perform the operation now. Try again later.
Articles 1–20