| Towards evaluating the robustness of neural networks N Carlini, D Wagner 2017 IEEE Symposium on Security and Privacy (SP), 39-57, 2017 | 1405 | 2017 |
| Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples A Athalye, N Carlini, D Wagner ICML 2018, 2018 | 567 | 2018 |
| 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 | 436 | 2017 |
| {ROP} is Still Dangerous: Breaking Modern Defenses N Carlini, D Wagner 23rd {USENIX} Security Symposium ({USENIX} Security 14), 385-399, 2014 | 279 | 2014 |
| 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 | 260 | 2015 |
| 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 | 237* | 2016 |
| Hidden Voice Commands. N Carlini, P Mishra, T Vaidya, Y Zhang, M Sherr, C Shields, D Wagner, ... USENIX Security Symposium, 513-530, 2016 | 226 | 2016 |
| Audio adversarial examples: Targeted attacks on speech-to-text N Carlini, D Wagner 2018 IEEE Security and Privacy Workshops (SPW), 1-7, 2018 | 183 | 2018 |
| 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 | 120 | 2017 |
| Defensive distillation is not robust to adversarial examples N Carlini, D Wagner arXiv preprint arXiv:1607.04311, 2016 | 118 | 2016 |
| An Evaluation of the Google Chrome Extension Security Architecture. N Carlini, AP Felt, D Wagner USENIX Security Symposium, 97-111, 2012 | 102 | 2012 |
| The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks N Carlini, C Liu, J Kos, Ú Erlingsson, D Song | 81* | 2019 |
| Magnet and "efficient defenses against adversarial attacks" are not robust to adversarial examples N Carlini, D Wagner arXiv preprint arXiv:1711.08478, 2017 | 78 | 2017 |
| Provably minimally-distorted adversarial examples N Carlini, G Katz, C Barrett, DL Dill arXiv preprint arXiv:1709.10207, 2017 | 56* | 2017 |
| On Evaluating Adversarial Robustness N Carlini, A Athalye, N Papernot, W Brendel, J Rauber, D Tsipras, ... arXiv preprint arXiv:1902.06705, 2019 | 51 | 2019 |
| On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses A Athalye, N Carlini arXiv preprint arXiv:1804.03286, 2018 | 49 | 2018 |
| MixMatch: A Holistic Approach to Semi-Supervised Learning D Berthelot, N Carlini, I Goodfellow, N Papernot, A Oliver, C Raffel arXiv preprint arXiv:1905.02249, 2019 | 30 | 2019 |
| Adversarial Examples Are a Natural Consequence of Test Error in Noise N Ford, J Gilmer, N Carlini, D Cubuk arXiv preprint arXiv:1901.10513, 2019 | 25 | 2019 |
| Unrestricted Adversarial Examples TB Brown, N Carlini, C Zhang, C Olsson, P Christiano, I Goodfellow arXiv preprint arXiv:1809.08352, 2018 | 20 | 2018 |
| Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition Y Qin, N Carlini, I Goodfellow, G Cottrell, C Raffel arXiv preprint arXiv:1903.10346, 2019 | 15 | 2019 |
