Export 10 results:
Filters: Author is Nicholas Carlini  [Clear All Filters]
Carlini N, Tramèr F, Wallace E, Jagielski M, Herbert-Voss A, Lee K, Roberts A, Brown T, Song D, Erlingsson Ú et al..  2021.  Extracting Training Data from Large Language Models. 30th USENIX Security Symposium (USENIX Security 21). :2633--2650.
Carlini N.  2021.  Poisoning the Unlabeled Dataset of Semi-Supervised Learning. 30th USENIX Security Symposium (USENIX Security 21). :1577--1592.
Jagielski M, Carlini N, Berthelot D, Kurakin A, Papernot N.  2020.  High Accuracy and High Fidelity Extraction of Neural Networks. 29th USENIX Security Symposium (USENIX Security 20). :1345--1362.
He W, Wei J, Chen X, Carlini N, Song D.  2017.  Adversarial Example Defense: Ensembles of Weak Defenses are not Strong. 11th USENIX Workshop on Offensive Technologies (WOOT 17).
Carlini N, Mishra P, Vaidya T, Zhang Y, Sherr M, Shields C, Wagner D, Zhou W.  2016.  Hidden Voice Commands. 25th USENIX Security Symposium (USENIX Security 16). :513--530.
Carlini N, Barresi A, Payer M, Wagner D, Gross TR.  2015.  Control-Flow Bending: On the Effectiveness of Control-Flow Integrity. 24th USENIX Security Symposium (USENIX Security 15). :161--176.
Carlini N, Wagner D.  2014.  ROP is Still Dangerous: Breaking Modern Defenses. 23rd USENIX Security Symposium (USENIX Security 14). :385--399.
Kim E, Carlini N, Chang A, Yiu G, Wang K, Wagner D.  2013.  Improved Support for Machine-assisted Ballot-level Audits. 2013 Electronic Voting Technology Workshop/Workshop on Trustworthy Elections (EVT/WOTE 13).
Carlini N, Felt APorter, Wagner D.  2012.  An Evaluation of the Google Chrome Extension Security Architecture. 21st USENIX Security Symposium (USENIX Security 12). :97--111.