activity
20242026
most citedWhen Eavesdroppers Reason: Agentic Eavesdropping Attacks on Semantic Communication

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

eess.SP2026★ 1 cited

When Eavesdroppers Reason: Agentic Eavesdropping Attacks on Semantic Communication

Shunpu Tang, Qianqian Yang, Zhiguo Shi +2

Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture a…

eess.SP2026

Rethinking Secure Semantic Communications in the Age of Generative and Agentic AI: Threats and Opportunities

Shunpu Tang, Yuanyuan Jia, Zijiu Yang +6

Semantic communication (SemCom) improves communication efficiency by transmitting task-relevant information instead of raw bits and is expected to be a key technology for 6G networ…

cs.IT2025

Can Knowledge Improve Security? A Coding-Enhanced Jamming Approach for Semantic Communication

Weixuan Chen, Qianqian Yang, Shuo Shao +4

As semantic communication (SemCom) attracts growing attention as a novel communication paradigm, ensuring the security of transmitted semantic information over open wireless channe…

eess.SY2025

Geometric Reachability for Attitude Control Systems via Contraction Theory

Chencheng Xu, Saber Jafarpour, Chengcheng Zhao +2

In this paper, we present a geometric framework for the reachability analysis of attitude control systems. We model the attitude dynamics on the product manifold $\mathrm{SO}(3) \t…

cs.CV2024

SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising

Tao Zhou, Wenhan Luo, Qi Ye +2

Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images. These promptabl…