Friday, 20 November 2026 Feeds updated just now CVE Tracker๐Ÿ‡ฎ๐Ÿ‡ณ IndiaEventsRSS
Primary

SCR: Detecting Backdoor-Poisoned Samples through Clean-Reference Residuals

arXiv cs.CR (Cryptography & Security) by Yi Yang, Jinyang Huang, Feng-Qi Cui, Yu-Tong Guo, Sirui Zhao, Haiming Jin, Weihua Li, Quan Bai, Meng Li Ingested 19 Nov 2026, 10:46
Primary source. Published by the vendor, CERT, regulator, government agency or researcher responsible.

arXiv:2611.24558v1 Announce Type: cross Abstract: Deep neural networks are vulnerable to backdoor attacks, in which adversaries manipulate model predictions by injecting poisoned samples into training data. Detecting these samples remains challenging because legitimate semantic variation can obscure poisoning-related signals in learned representations. Consequently, class-level statistics used byโ€ฆ

Read the full story at arXiv cs.CR (Cryptography & Security) โ†—

HackerNews24 shows a short summary only. The full article, its copyright and any corrections belong to the original publisher.