University of Minnesota
Security and Privacy in Computing
index.php

Readings on: Security of machine learning

Reading for Thursday, March 24th: Roei Schuster, Congzheng Song, Eran Tromer, and Vitaly Shmatikov. “You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion.” In USENIX Security Symposium, August 2021.
[USENIX]

Reading for Tuesday, March 22nd: Nicholas Carlini. “Poisoning the Unlabeled Dataset of Semi-Supervised Learning.” In USENIX Security Symposium, August 2021.
[USENIX]

Candidate reading: Giulio Lovisotto, Henry Turner, Ivo Sluganovic, Martin Strohmeier, and Ivan Martinovic. “SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations.” In USENIX Security Symposium, August 2021.
[USENIX]

Candidate reading: Chong Xiang and Prateek Mittal. “DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks.” In ACM CCS, November 2021.
[ACM DL]