4 papers
SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption
Zhiqiang Wang, Haohua Du, Junyang Wang +5
Large language models (LLMs) with diverse capabilities are increasingly being deployed in local environments, presenting significant security and controllability challenges. These…
Measuring Discrete Sensing Capability for ISAC via Task Mutual Information
Fei Shang, Haohua Du, Panlong Yang +3
6G technology offers a broader range of possibilities for communication systems to perform ubiquitous sensing tasks, including health monitoring, object recognition, and autonomous…
The Field-based Model: A New Perspective on RF-based Material Sensing
Fei Shang, Haocheng Jiang, Panlong Yang +3
This paper introduces the design and implementation of WiField, a WiFi sensing system deployed on COTS devices that can simultaneously identify multiple wavelength-level targets pl…
SGSM: A Foundation-model-like Semi-generalist Sensing Model
Tianjian Yang, Hao Zhou, Shuo Liu +5
The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations f…