all InfoSec news
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
March 4, 2024, 5:10 a.m. | Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
cs.CR updates on arXiv.org arxiv.org
Abstract: Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker injects poisoned inputs into the pre-training dataset so the encoder is backdoored. However, existing DPBAs achieve limited effectiveness. In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL. CorruptEncoder …
arxiv attacker attacks backdoor backdoor attacks cs.cr cs.cv cs.lg data data poisoning dataset general image images inputs poisoning purpose text training trains vulnerable
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
SITEC- Systems Security Administrator- Camp HM Smith
@ Peraton | Camp H.M. Smith, HI, United States
Cyberspace Intelligence Analyst
@ Peraton | Fort Meade, MD, United States
General Manager, Cybersecurity, Google Public Sector
@ Google | Virginia, USA; United States
Cyber Security Advisor
@ H&M Group | Stockholm, Sweden
Engineering Team Manager – Security Controls
@ H&M Group | Stockholm, Sweden