2 papers
cs.CR2025
Backdoor Attack with Invisible Triggers Based on Model Architecture Modification
Yuan Ma, Jiankang Wei, Yilun Lyu +2
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor a…
cs.CV2025
Enhancing Sentiment Analysis through Multimodal Fusion: A BERT-DINOv2 Approach
Taoxu Zhao, Meisi Li, Kehao Chen +6
Multimodal sentiment analysis enhances conventional sentiment analysis, which traditionally relies solely on text, by incorporating information from different modalities such as im…