USENIX supports diversity, equity, and inclusion and condemns hate and discrimination.
Biblio
Export 11 results:
Filters: Author is Nicholas Carlini [Clear All Filters]
Tight Auditing of Differentially Private Machine Learning. 32nd USENIX Security Symposium (USENIX Security 23). :1631--1648.
.
2023. Extracting Training Data from Large Language Models. 30th USENIX Security Symposium (USENIX Security 21). :2633--2650.
.
2021. Poisoning the Unlabeled Dataset of Semi-Supervised Learning. 30th USENIX Security Symposium (USENIX Security 21). :1577--1592.
.
2021. High Accuracy and High Fidelity Extraction of Neural Networks. 29th USENIX Security Symposium (USENIX Security 20). :1345--1362.
.
2020. The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks. 28th USENIX Security Symposium (USENIX Security 19). :267--284.
.
2019. Adversarial Example Defense: Ensembles of Weak Defenses are not Strong. 11th USENIX Workshop on Offensive Technologies (WOOT 17).
.
2017. Hidden Voice Commands. 25th USENIX Security Symposium (USENIX Security 16). :513--530.
.
2016. Control-Flow Bending: On the Effectiveness of Control-Flow Integrity. 24th USENIX Security Symposium (USENIX Security 15). :161--176.
.
2015. ROP is Still Dangerous: Breaking Modern Defenses. 23rd USENIX Security Symposium (USENIX Security 14). :385--399.
.
2014. Improved Support for Machine-assisted Ballot-level Audits. 2013 Electronic Voting Technology Workshop/Workshop on Trustworthy Elections (EVT/WOTE 13).
.
2013. An Evaluation of the Google Chrome Extension Security Architecture. 21st USENIX Security Symposium (USENIX Security 12). :97--111.
.
2012.