On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned ML Models
Industry experts analyze emerging threats surrounding On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned ML Models.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
IEEE Symposium on Security and Privacy·15 min
Industry experts analyze emerging threats surrounding Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers.
backdoorjigsawpuzzle+3
HITCON·48 min
Engineers explore architecture and security mechanisms for 2021 - Analysis of Invisible Data Poisoning Backdoor Attacks against Malware Classifiers.
backdooranalysiinvisible+1
Videos·24 min
Peter Kálnai (ESET)
Reviews lazarus campaigns and backdoors in 2022 2023 and evaluates key implications for security practitioners.
lazarucampaignbackdoor