While Vision-Language Models (VLMs) excel at multimodal tasks, they are increasingly vulnerable to sophisticated multimodal jailbreak attacks. Conventional defenses typically introduce significant training overhead, risk degrading model capabilities, or cause severe inference latency via external modules. Additionally,...
Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al.· Proceedings of the 34th ACM...· 0 citations
Dual-grained Internal Refusal Estimation (DIRE), a training-free detection framework that jointly probes resilient Attention routing and FFN semantic memory within effective semantic layers to detect multimodal jailbreaks in a training-free manner, is introduced.
Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al.· Proceedings of the 34th ACM...· 0 citations
This work proposes a lightweight dual-domain attention aggregation network (LDANet), aiming to achieve image super-resolution with both high efficiency and high quality, and proposes the pixel-embedding channel attention module, which achieves cross-channel global context awareness by jointly modeling pixel-level spati...
Wei Xue, Meng-Cheng Ma, Bing-Wen Hu et al.· ACM Transactions on Multimed...· 0 citations
SpectraMancer, which learns kernels directly in the Fourier spectral domain induced by multilevel circulant matrices, thereby enabling generalizable kernel learning for complex data and improves spectrum-aware kernel selection and predictive performance across diverse benchmarks.
Li-Zhong Ding, Jiarun Fu, Qiuning Wei et al.· IEEE Transactions on Neural...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.