Latest News
- Recently Published in IEEE ANTS 2024.
- Recently Published in AIoT@MOBIHOC2024
Ongoing Research
- Research Topic 1: Network implications of wireless sensing.
- Research Topic 2: Adversarial Wi-Fi sensing.
Research Work
Practical Defense Against Adversarial WiFi Sensing(IEEE ANTS 2024)
Non-intrusive approach of WiFi-based sensing has expanded its market presence. It leverages existing communication infrastructure, extracting Channel State Information (CSI) for area assessment. However, the method’s susceptibility to misuse, termed the Integrated Sensing and Communication (ISAC) problem, necessitates robust defenses. Our study introduces a black-box defense against adversarial attacks on CSI, reducing classification model accuracy from 98% to 17% while maintain ing strong communication throughput. Additionally, our method preserves a median Signal-to-Noise Ratio (SNR) difference of 1dB for perturbed samples, enhancing overall system reliability.
Improving Network Resource Utilization for Distributed Wireless Sensing Applications(AIoT@MobiHoc2024)
Edge-assisted wireless sensing is increasingly popular, where complex neural network models perform inference tasks on wireless channel state information (CSI) data streamed from IoT devices. However large volumes of CSI data sent across the network for inference can significantly impact network bandwidth and reduce the Quality of Experience. This work tackles the challenge of optimizing network resource utilization in wireless sensing systems by compressing and subsampling CSI streams. We evaluate methods that quantize and selectively subsample CSI data before transmission to the edge server, which is then fed to the inference models. Such approach reduces bandwidth and computational load, improving data transmission and processing efficiency. Experiments conducted in two real testbeds (indoors as well as outdoors) show how CSI compression preserves sensing information integrity while enhancing system performance in terms of latency, energy efficiency, and throughput. By integrating quantization and subsampling with edge computing, this work enhances wireless sensing systems, making them more scalable and efficient in utilizing network resources.
Contact Information
If you'd like to get in touch, you can reach me at:
- Email: cs22d002@cse.iitm.ac.in
- Lab Address: Lab 423, SSB block Computer Science Dept. IIT Madras, Chennai-600036 Tamil Nadu, India