| Fawkes: Protecting privacy against unauthorized deep learning models S Shan, E Wenger, J Zhang, H Li, H Zheng, BY Zhao 29th USENIX security symposium (USENIX Security 20), 1589-1604, 2020 | 342 | 2020 |
| Backdoor attacks against deep learning systems in the physical world E Wenger, J Passananti, AN Bhagoji, Y Yao, H Zheng, BY Zhao Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 271* | 2021 |
| Glaze: Protecting artists from style mimicry by {Text-to-Image} models S Shan, J Cryan, E Wenger, H Zheng, R Hanocka, BY Zhao 32nd USENIX Security Symposium (USENIX Security 23), 2187-2204, 2023 | 223 | 2023 |
| Gotta catch'em all: Using honeypots to catch adversarial attacks on neural networks S Shan, E Wenger, B Wang, B Li, H Zheng, BY Zhao Proceedings of the 2020 ACM SIGSAC conference on computer and communications …, 2020 | 108 | 2020 |
| Blacklight: Defending black-box adversarial attacks on deep neural networks H Li, S Shan, E Wenger, J Zhang, H Zheng, BY Zhao arXiv preprint arXiv:2006.14042 3, 2020 | 105* | 2020 |
| Piracy resistant watermarks for deep neural networks H Li, E Wenger, S Shan, BY Zhao, H Zheng arXiv preprint arXiv:1910.01226, 2019 | 79* | 2019 |
| “Hello, It’s Me”: Deep Learning-based Speech Synthesis Attacks in the Real World E Wenger, M Bronckers, C Cianfarani, J Cryan, A Sha, H Zheng, BY Zhao | 58 | 2021 |
| Salsa: Attacking lattice cryptography with transformers E Wenger, M Chen, F Charton, KE Lauter Advances in Neural Information Processing Systems 35, 34981-34994, 2022 | 42 | 2022 |
| Finding Naturally Occurring Physical Backdoors in Image Datasets E Wenger, R Bhattacharjee, AN Bhagoji, J Passananti, E Andere, ... Thirty-sixth Conference on Neural Information Processing Systems Datasets …, 2022 | 27* | 2022 |
| Sok: Anti-facial recognition technology E Wenger, S Shan, H Zheng, BY Zhao 2023 IEEE Symposium on Security and Privacy (SP), 864-881, 2023 | 25 | 2023 |
| SALSA VERDE: a machine learning attack on LWE with sparse small secrets C Li, E Wenger, Z Allen-Zhu, F Charton, KE Lauter Advances in Neural Information Processing Systems 36, 53343-53361, 2023 | 15 | 2023 |
| Data isotopes for data provenance in DNNs E Wenger, X Li, BY Zhao, V Shmatikov arXiv preprint arXiv:2208.13893, 2022 | 14 | 2022 |
| Salsapicante: a machine learning attack on LWE with binary secrets CY Li, J Sotáková, E Wenger, M Malhou, E Garcelon, F Charton, K Lauter Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications …, 2023 | 13 | 2023 |
| Post-breach recovery: Protection against white-box adversarial examples for leaked dnn models S Shan, W Ding, E Wenger, H Zheng, BY Zhao Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications …, 2022 | 13 | 2022 |
| AI produces gibberish when trained on too much AI-generated data E Wenger Nature 631 (8022), 742-743, 2024 | 6 | 2024 |
| SALSA FRESCA: angular embeddings and pre-training for ML attacks on learning with errors S Stevens, E Wenger, C Li, N Nolte, E Saxena, F Charton, K Lauter arXiv preprint arXiv:2402.01082, 2024 | 6 | 2024 |
| The cool and the cruel: separating hard parts of LWE secrets N Nolte, M Malhou, E Wenger, S Stevens, C Li, F Charton, K Lauter International Conference on Cryptology in Africa, 428-453, 2024 | 2 | 2024 |
| Assessing privacy risks from feature vector reconstruction attacks E Wenger, F Falzon, J Passananti, H Zheng, BY Zhao arXiv preprint arXiv:2202.05760, 2022 | 2 | 2022 |
| Teaching Transformers Modular Arithmetic at Scale E Saxena, A Alfarano, E Wenger, K Lauter arXiv preprint arXiv:2410.03569, 2024 | 1 | 2024 |
| Benchmarking Attacks on Learning with Errors E Wenger, E Saxena, M Malhou, E Thieu, K Lauter arXiv preprint arXiv:2408.00882, 2024 | 1 | 2024 |
Ben Y. ZhaoNeubauer Professor of Computer Science, University of ChicagoVerified email at uchicago.edu
