Google Research
Tousif Ahmed

Tousif Ahmed

Tousif Ahmed is a Privacy Engineer and Applied Privacy Researcher at the Devices and Services Team (DSPA). Tousif works on improving and designing privacy-preserving technologies in Google Hardware devices, including Pixel, Fitbit, and Nest, so he is interested in topics related to mobile, wearable, and smart home devices, including sensor privacy, privacy of multimodal devices, IoT privacy, health information privacy, camera privacy, and bystander privacy. Tousif received my Ph.D. in Computer Science from the Indiana University Bloomington. Tousif's PhD research is one of the very first works that considered the privacy and security concerns of the visually impaired and has inspired subsequent research in usable privacy and security, as well as in accessibility. Due to his contribution, he received John Karat Usable Privacy and Security Student Research Award in 2019. Tousif published more than 30 papers in top-tier conferences, including CHI, CSCW, ASSETS, Ubicomp, and SOUPS.

Research Areas

Authored Publications
results

Publications

Years

Research Areas

Teams

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
What’s on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
Rameen Mahmood
Sai Teja Peddinti
Tousif Ahmed
Danny Yuxing Huang
Proceedings of ACM International Conference on Emerging Networking Experiments and Technologies (CoNEXT), Association for Computing Machinery (2026)
Preview abstract The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability. This challenge is especially pronounced in open‑world environments, where network traffic metadata is often sparse, noisy, or adversarial. To address this problem, we introduce a semantic inference pipeline that reframes device identification as a language modeling task over real‑world network metadata. As this approach depends on reliable supervision, we first construct high‑fidelity vendor labels for the IoT Inspector dataset—the largest real‑world corpus of its kind—using an ensemble of large language models guided by mutual‑information and entropy‑based stability scores. We then instruction-tune a quantized LLaMA 3.1 8B model on this dataset using curriculum learning to support generalization under sparsity and long-tail vendor distributions. Our model achieves 98.69% top-1 and 90.73% macro accuracy across 2,015 vendors, while remaining robust to missing fields, protocol drift, and adversarial manipulation. We also evaluate the model on an independent IoT testbed dataset, assess explanation quality, and conduct adversarial tests to probe robustness under spoofed and obfuscated input. These results position instruction-tuned LLMs as a scalable, interpretable foundation for trustworthy device identification at scale. View details
Search on Google Scholar
×