all AI news
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
March 26, 2024, 4:47 a.m. | Siyuan Liang, Kuanrong Liu, Jiajun Gong, Jiawei Liang, Yuan Xun, Ee-Chien Chang, Xiaochun Cao
cs.CV updates on arXiv.org arxiv.org
Abstract: Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the possibility of backdoor attacks. These attacks subtly embed malicious behaviors within the model during training, which can be activated by specific triggers in the inference phase, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the adverse impacts of such attacks, these …
abstract arxiv attacks backdoor building cs.cv data defense embed features however multimodal nature paradigm possibility quality systems threats token type unlearning via
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Data Engineer
@ Kaseya | Bengaluru, Karnataka, India