Biblio

Export 3 results:
Filters: Author is Varun Chandrasekaran  [Clear All Filters]
2021
Jia H, Choquette-Choo CA, Chandrasekaran V, Papernot N.  2021.  Entangled Watermarks as a Defense against Model Extraction. 30th USENIX Security Symposium (USENIX Security 21). :1937--1954.
Chandrasekaran V, Banerjee S, Mutlu B, Fawaz K.  2021.  PowerCut and Obfuscator: An Exploration of the Design Space for Privacy-Preserving Interventions for Smart Speakers. Seventeenth Symposium on Usable Privacy and Security (SOUPS 2021). :535--552.
2020
Chandrasekaran V, Chaudhuri K, Giacomelli I, Jha S, Yan S.  2020.  Exploring Connections Between Active Learning and Model Extraction. 29th USENIX Security Symposium (USENIX Security 20). :1309--1326.