Explore a 15-minute IEEE conference talk on efficient, high-fidelity, and blind suppression of backdoor effects in trojaned machine learning models. Delve into the concept of "Selective Amnesia" presented by researchers from Indiana University Bloomington, including Rui Zhu, Di Tang, Siyuan Tang, XiaoFeng Wang, and Haixu Tang. Learn about innovative techniques to mitigate backdoor vulnerabilities in ML models while maintaining their performance and functionality.
Selective Amnesia - On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Overview
Syllabus
On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned ML Models
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
RAB - Provable Robustness Against Backdoor Attacks
-
BadEncoder - Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
-
Jigsaw Puzzle - Selective Backdoor Attack to Subvert Malware Classifiers
-
REDEEM MYSELF - Purifying Backdoors in Deep Learning Models Using Self Attention Distillation
-
Adversarial Examples for Proof-of-Learning
-
SoK - Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
