all InfoSec news
Backdoor Contrastive Learning via Bi-level Trigger Optimization
April 12, 2024, 4:11 a.m. | Weiyu Sun, Xinyu Zhang, Hao Lu, Yingcong Chen, Ting Wang, Jinghui Chen, Lu Lin
cs.CR updates on arXiv.org arxiv.org
Abstract: Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack target class, thus fooling the downstream predictor to misclassify it as the target. Existing attacks usually adopt a fixed trigger pattern and poison the training set with trigger-injected data, hoping for the feature …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Security Engineer
@ SNC-Lavalin | GB.Bristol.The Hub
Application Security Engineer
@ Virtru | Remote
SC2024-003563 Firewall Coordinator (NS) - TUE 21 May
@ EMW, Inc. | Mons, Wallonia, Belgium
Senior Application Security Engineer
@ Fortis Games | Remote - Canada
DevSecOps Manager
@ Philips | Bengaluru – Embassy Business Hub
Information System Security Manager (ISSM)
@ ARA | Raleigh, North Carolina, United States