Biblio

Export 3 results:
Filters: Author is Guozhu Meng  [Clear All Filters]
2023
Wei C'an, Lee Y, Chen K, Meng G, Lv P.  2023.  Aliasing Backdoor Attacks on Pre-trained Models. 32nd USENIX Security Symposium (USENIX Security 23). :2707--2724.
Deng Z, Meng G, Chen K, Liu T, Xiang L, Chen C.  2023.  Differential Testing of Cross Deep Learning Framework APIs: Revealing Inconsistencies and Vulnerabilities. 32nd USENIX Security Symposium (USENIX Security 23). :7393--7410.
2021
He Y, Meng G, Chen K, Hu X, He J.  2021.  DRMI: A Dataset Reduction Technology based on Mutual Information for Black-box Attacks. 30th USENIX Security Symposium (USENIX Security 21). :1901--1918.