| Towards evaluating the robustness of neural networks N Carlini, D Wagner 2017 IEEE Symposium on Security and Privacy (SP), 39-57, 2017 | 6777 | 2017 |
| Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples A Athalye, N Carlini, D Wagner ICML 2018, 2018 | 2694 | 2018 |
| Mixmatch: A holistic approach to semi-supervised learning D Berthelot, N Carlini, I Goodfellow, N Papernot, A Oliver, CA Raffel Advances in Neural Information Processing Systems, 5050-5060, 2019 | 2058 | 2019 |
| FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence K Sohn, D Berthelot, CL Li, Z Zhang, N Carlini, ED Cubuk, A Kurakin, ... arXiv preprint arXiv:2001.07685, 2020 | 1679 | 2020 |
| Adversarial examples are not easily detected: Bypassing ten detection methods N Carlini, D Wagner Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security …, 2017 | 1652 | 2017 |
| Audio adversarial examples: Targeted attacks on speech-to-text N Carlini, D Wagner 2018 IEEE Security and Privacy Workshops (SPW), 1-7, 2018 | 1022 | 2018 |
| The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks N Carlini, C Liu, J Kos, Ú Erlingsson, D Song | 760* | 2019 |
| ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring D Berthelot, N Carlini, ED Cubuk, A Kurakin, K Sohn, H Zhang, C Raffel arXiv preprint arXiv:1911.09785, 2019 | 706 | 2019 |
| On Evaluating Adversarial Robustness N Carlini, A Athalye, N Papernot, W Brendel, J Rauber, D Tsipras, ... arXiv preprint arXiv:1902.06705, 2019 | 684 | 2019 |
| Hidden Voice Commands. N Carlini, P Mishra, T Vaidya, Y Zhang, M Sherr, C Shields, D Wagner, ... USENIX Security Symposium, 513-530, 2016 | 650 | 2016 |
| cleverhans v2. 0.0: an adversarial machine learning library N Papernot, N Carlini, I Goodfellow, R Feinman, F Faghri, A Matyasko, ... arXiv preprint arXiv:1610.00768, 2016 | 610* | 2016 |
| On adaptive attacks to adversarial example defenses F Tramer, N Carlini, W Brendel, A Madry Advances in Neural Information Processing Systems 33, 1633-1645, 2020 | 551 | 2020 |
| Control-flow bending: On the effectiveness of control-flow integrity N Carlini, A Barresi, M Payer, D Wagner, TR Gross 24th {USENIX} Security Symposium ({USENIX} Security 15), 161-176, 2015 | 483 | 2015 |
| Extracting Training Data from Large Language Models. N Carlini, F Tramer, E Wallace, M Jagielski, A Herbert-Voss, K Lee, ... USENIX Security Symposium 6, 2021 | 480 | 2021 |
| Provably minimally-distorted adversarial examples N Carlini, G Katz, C Barrett, DL Dill arXiv preprint arXiv:1709.10207, 2017 | 454* | 2017 |
| {ROP} is Still Dangerous: Breaking Modern Defenses N Carlini, D Wagner 23rd {USENIX} Security Symposium ({USENIX} Security 14), 385-399, 2014 | 453 | 2014 |
| Adversarial example defense: Ensembles of weak defenses are not strong W He, J Wei, X Chen, N Carlini, D Song 11th {USENIX} Workshop on Offensive Technologies ({WOOT} 17), 2017 | 368 | 2017 |
| Imperceptible, robust, and targeted adversarial examples for automatic speech recognition Y Qin, N Carlini, G Cottrell, I Goodfellow, C Raffel International Conference on Machine Learning, 5231-5240, 2019 | 335 | 2019 |
| Defensive distillation is not robust to adversarial examples N Carlini, D Wagner arXiv preprint arXiv:1607.04311, 2016 | 323 | 2016 |
| Adversarial examples are a natural consequence of test error in noise J Gilmer, N Ford, N Carlini, E Cubuk International Conference on Machine Learning, 2280-2289, 2019 | 281* | 2019 |
David WagnerProfessor of Computer Science, UC BerkeleyVerified email at cs.berkeley.edu
