Arvin Hekmati

Xin Wang, Zhongwei Wan, Arvin Hekmati et al.

Advancements in Generative AI hold immense promise to push Internet of Things (IoT) to the next level. In this article, we share our vision on IoT in the era of Generative AI. We discuss some of the most important applications of Generative AI in IoT-related domains. We also identify some of the most critical challenges and discuss current gaps as well as promising opportunities on enabling Generative AI for IoT. We hope this article can inspire new research on IoT in the era of Generative AI.

Mingyu Zong, Arvin Hekmati, Michael Guastalla et al.

This paper identifies and analyzes applications in which Large Language Models (LLMs) can make Internet of Things (IoT) networks more intelligent and responsive through three case studies from critical topics: DDoS attack detection, macroprogramming over IoT systems, and sensor data processing. Our results reveal that the GPT model under few-shot learning achieves 87.6% detection accuracy, whereas the fine-tuned GPT increases the value to 94.9%. Given a macroprogramming framework, the GPT model is capable of writing scripts using high-level functions from the framework to handle possible incidents. Moreover, the GPT model shows efficacy in processing a vast amount of sensor data by offering fast and high-quality responses, which comprise expected results and summarized insights. Overall, the model demonstrates its potential to power a natural language interface. We hope that researchers will find these case studies inspiring to develop further.

Arvin Hekmati, Eugenio Grippo, Bhaskar Krishnamachari

As IoT deployments grow in scale for applications such as smart cities, they face increasing cyber-security threats. In particular, as evidenced by the famous Mirai incident and other ongoing threats, large-scale IoT device networks are particularly susceptible to being hijacked and used as botnets to launch distributed denial of service (DDoS) attacks. Real large-scale datasets are needed to train and evaluate the use of machine learning algorithms such as deep neural networks to detect and defend against such DDoS attacks. We present a dataset from an urban IoT deployment of 4060 nodes describing their spatio-temporal activity under benign conditions. We also provide a synthetic DDoS attack generator that injects attack activity into the dataset based on tunable parameters such as number of nodes attacked and duration of attack. We discuss some of the features of the dataset. We also demonstrate the utility of the dataset as well as our synthetic DDoS attack generator by using them for the training and evaluation of a simple multi-label feed-forward neural network that aims to identify which nodes are under attack and when.

Arvin Hekmati, Gowri Ramachandran, Bhaskar Krishnamachari

Pandemic and epidemic diseases such as CoVID-19, SARS-CoV2, and Ebola have spread to multiple countries and infected thousands of people. Such diseases spread mainly through person-to-person contacts. Health care authorities recommend contact tracing procedures to prevent the spread to a vast population. Although several mobile applications have been developed to trace contacts, they typically require collection of privacy-intrusive information such as GPS locations, and the logging of privacy-sensitive data on a third party server, or require additional infrastructure such as WiFi APs with known locations. In this paper, we introduce CONTAIN, a privacy-oriented mobile contact tracing application that does not rely on GPS or any other form of infrastructure-based location sensing, nor the continuous logging of any other personally identifiable information on a server. The goal of CONTAIN is to allow users to determine with complete privacy if they have been within a short distance, specifically, Bluetooth wireless range, of someone that is infected, and potentially also when. We identify and prove the privacy guarantees provided by our approach. Our simulation study utilizing an empirical trace dataset (Asturies) involving 100 mobile devices and around 60000 records shows that users can maximize their possibility of identifying if they were near an infected user by turning on the app during active times.