publications

2024

1. Music to My Ears: Turning GPU Sounds into Intellectual Property Gold

   Arefin, Sayed Erfan, and Serwadda, Abdul

   In Proceedings of the 2024 Workshop on Artificial Intelligence and Security 2024

   Abs PDF Poster

   In this paper, we introduce an acoustic side-channel attack that extracts crucial information from Deep Neural Networks (DNNs) operating on GPUs. Utilizing a Micro-Electro-Mechanical Systems (MEMS) microphone with an extensive frequency range, we demonstrate that the distinct sounds produced during DNN operations can inadvertently reveal significant details about the network’s architecture. Through extensive experimentation with a variety of neural networks from the ImageNet competition, we validate the efficacy of this novel attack vector. Our contributions include a detailed methodological framework for capturing and analyzing acoustic data, empirical validation using prominent ImageNet models, and a comprehensive sensitivity analysis to assess the attack’s robustness under varying conditions. This research not only uncovers a previously unexplored vulnerability in neural network security but also provides a foundation for developing more robust defense mechanisms against such innovative side-channel attacks.

2. The Road to Web 3.0: Empirical Insights into Full Node Workload in the Bitcoin Blockchain

   Arefin, Sayed Erfan, and Serwadda, Abdul

   In 2024 International Conference on Smart Applications, Communications and Networking (SmartNets) May 2024

   Abs PDF Slides

   The shift from Web 2.0 to Web 3.0, known as the “decentralized web”, hinges crucially on end-user engagement, particularly in the hosting of blockchain nodes. This study delves into the operational requirements for maintaining Bitcoin full nodes by comparing the experiences of two distinct setups: a high-specification desktop and a low-resource Single Board Computer. We meticulously analyze the implications of these setups on end-user resources, focusing on power consumption, bandwidth usage, and data traffic patterns. The findings not only highlight the practical challenges users will encounter in the evolving digital landscape but also provide new insights into the dynamics of the Bitcoin blockchain, particularly during a period of significant market volatility.

3. Stable or Shaky? The Semantics of ChatGPT’s Behavior Under Repeated Queries

   Heya, Tasnia Ashrafi, Ineza, Ynes,  Arefin, Sayed Erfan, Uzor, Godsgift, and Serwadda, Abdul

   In 2024 IEEE 18th International Conference on Semantic Computing (ICSC) Feb 2024

   Abs

   Large Language Models (LLMs) like ChatGPT have propelled artificial intelligence to new heights, demonstrating remarkable aptitude across various disciplines. Yet, most studies that have investigated the performance of these models in the wild have not fully captured the nuanced performance characteristics of these models, particularly in terms of response stability — a crucial attribute for their application and development. This study zeroes in on this underexplored facet by examining ChatGPT’s consistency when answering identical queries repeatedly. Employing a robust set of 741 questions, each reiterated 15 times, we deploy an array of analytical metrics to dissect the model’s consistency profile. Our investigation provides a novel benchmark for ChatGPT’s accuracy within a repetitive context, marking a departure from the prevalent approach of assessing LLMs across diverse single-instance prompts. The outcomes of this study are instrumental in delineating the robustness of state-of-the-art LLMs in scenarios where reliable consistency is imperative, such as educational contexts and critical decision-making processes. By systematically characterizing ChatGPT’s consistency patterns, our work lays the groundwork for targeted enhancements and offers a set of benchmarks crucial for future work aimed at optimizing the stability and reliability of AI-generated responses.

4. Dissecting the Origins of the Power Side-Channel in Deep Neural Networks

   Arefin, Sayed Erfan, and Serwadda, Abdul

   In 2024 IEEE World AI IoT Congress (AIIoT) May 2024

   Abs Slides

   In this study, we investigate the vulnerability of Deep Neural Networks (DNNs) to architectural inference via software-based power consumption analysis on GPUs. This work introduces the use of Nvidia-smi, an important tool pre-installed with Nvidia drivers, enabling us to bypass additional software requirements on the target computer. We delve into the distinct power footprints of specific neural networks, look into the units of neural networks, and introduce mitigation techniques. With a widened scope encompassing six different GPU platforms, ranging from physical to the latest high-end cloud-based units, our experiments reveal nuanced insights. This research underscores the effectiveness of power draw patterns in exposing DNN architectures and the critical importance of adopting countermeasures to safeguard intellectual property in the age of advanced machine learning technologies.

5. Unmasking the Giant: A Comprehensive Evaluation of ChatGPT’s Proficiency in Coding Algorithms and Data Structures

   Arefin., Sayed, Heya., Tasnia, Al-Qudah., Hasan, Ineza., Ynes, and Serwadda., Abdul

   May 2024

   Abs PDF Poster

   We conduct an extensive analysis of ChatGPT, a standout Large Language Model (LLM), particularly in coding within the Python language, focusing on data structures and algorithms. We assess ChatGPT’s ability to accurately solve coding problems, its code quality, and the nature of run-time errors. Additionally, we examine how ChatGPT’s code performs when it executes but doesn’t solve the problem, identifying error patterns. We also explore whether ChatGPT has memorized training data through a structured experiment. Comparing with human performance where possible, our study encompasses both GPT-3.5 and GPT-4 models, various subtopics within the main areas, and problems of different complexities.

2022

1. Weaponizing IoT Sensors: When Table Choice Poses a Security Vulnerability

   Casqueiro, Gustavo,  Arefin, Sayed Erfan, Ashrafi Heya, Tasnia, Serwadda, Abdul, and Wasswa, Hassan

   In 2022 IEEE 4th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA) May 2022

   PDF Slides

2021

1. Deep Neural Exposure: You Can Run, But Not Hide Your Neural Network Architecture!

   Arefin, Sayed Erfan, and Serwadda, Abdul

   In Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security May 2021

   Abs PDF Slides

   Deep Neural Networks (DNNs) are at the heart of many of today’s most innovative technologies. With companies investing lots of resources to design, build and optimize these networks for their custom products, DNNs are now integral to many companies’ tightly guarded Intellectual Property. As is the case for every high-value product, one can expect bad actors to increasingly design techniques aimed to uncover the architectural designs of proprietary DNNs. This paper investigates if the power draw patterns of a GPU on which a DNN runs could be leveraged to glean key details of its design architecture. Based on ten of the most well-known Convolutional Neural Network (CNN) architectures, we study this line of attack under varying assumptions about the kind of data available to the attacker. We show the attack to be highly effective, attaining an accuracy in the 80 percentage range for the best performing attack scenario.

2. Second Hand Price Prediction for Tesla Vehicles

   Arefin, Sayed Erfan

   CoRR May 2021
3. Predictive Analysis of Chikungunya

   Arefin, Sayed Erfan, Ashrafi, Tasnia Heya, and Zaber, Moinul

   CoRR May 2021

2019

1. Agent Based Fog Architecture using NDN and Trust Management for IoT

   Arefin, Sayed Erfan, Heya, Tasnia Ashrafi, and Chakrabarty, Amitabha

   In TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON) May 2019

2018

1. IoT Infrastructure: Fog Computing Surpasses Cloud Computing

   Ashrafi, Tasnia H., Hossain, Md. Arshad, Arefin, Sayed E., Das, Kowshik D. J., and Chakrabarty, Amitabha

   In Intelligent Communication and Computational Technologies May 2018

   Abs

   The Internet of Things can be defined as an expansion of Internet network further off conventional gadgets like computers, smart phones, and tablets to an assorted scope of gadgets and ordinary things that use embedded technology to communicate with the outer environment, all by means of the Internet. With the increasing time, data access and computing are proceeding towards more complications and hurdles requiring more efficient and logical data computation infrastructures but the vision of future IoT seems foggy as it is a matter of concern that our current infrastructure may not be able to handle large amount of data efficiently involving growing number of IoT devices. To get diminished from this issue, Fog computing has been introduced which is an expansion of cloud computing working as a decentralized infrastructure in which reserving or computing data, service, and applications are distributed in the most efficient and logical position between source and the cloud. In this paper, the current infrastructure has been depicted and proposed another model of IoT infrastructure to surpass the difficulties of the existing infrastructure, which will be a coordinated effort of Fog computing amalgamation with Machine-to-Machine (M2M) intelligent communication protocol followed by incorporation of Service-Oriented Architecture (SOA) and finally integration of agent-based SOA. This model will have the capacity to exchange data by breaking down dependably and methodically with low latency, less bandwidth, heterogeneity in less measure of time maintaining the Quality of Service (QoS) precisely.

2. Image Processing Based Indoor Localization System for Assisting Visually Impaired People

   Heya, Tasnia Ashrafi,  Arefin, Sayed Erfan, Chakrabarty, Amitabha, and Alam, Mazidul

   In 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) Mar 2018

   Abs

   Indoor localization or indoor positioning system is a known as a process of detecting position of any object or people inside a building or room by different sensory data collected from different devices using different techniques such as radio waves, magnetic fields, acoustic signals or other procedures. However, lacking of a standard localization system is still a very big concern. Solution of this issue can be very beneficial for people in many cases but it can be especially very beneficial for the visually impaired people. In this paper, an image processing based indoor localization system has been developed using OpenCV and Python by following color detection technique to detect position of the user with maximum accuracy and then location of user is determined by analyzing that location matrix. Location accuracy depends on the size of the matrix and successful identification of target color. Firebase real time database was added to the system which made real time operations between server and the user end device easier. To justify the proposed model, successful experiments were conducted in indoor environments as well and correct result was achieved each time by detecting accurate locations. This will be very advantageous to observe the fully or partially sightless people and guide them towards their destination and also to inspect them for their security purpose.

3. Real-life Implementation of Internet of Robotic Things Using 5 DoF Heterogeneous Robotic Arm

   Arefin, Sayed Erfan, Ashrafi Heya, Tasnia, and Uddin, Jia

   In 2018 Joint 7th International Conference on Informatics, Electronics Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision Pattern Recognition (icIVPR) Mar 2018
4. A Novel Extended-Cloud Based Approach for Internet of Things

   Chakrabarty, Amitabha, Heya, Tasnia Ashrafi, Hossain, Md. Arshad,  Arefin, Sayed Erfan, and Joy, Kowshik Dipta Das

   Mar 2018

   Abs

   The Internet of Things(IoT) is the future Internet evolution towards a network of interconnected smart objects such as computers, smart phones, smart watches, smart televisions, smart cars and many more. It is a matter of concern that our current infrastructure may not be able to handle large amount of data efficiently involving the growing number of smart IoT devices. As a solution, in this paper we came up with proposing a hybrid model of IoT infrastructure, as compared to the existing infrastructure to overcome its challenges. Our proposed infrastructure will be a collaboration of Fog computing combined with intelligent use of Service Oriented Architecture(SOA) which will be serving as a machine to machine communication protocol. This model will be able to transfer data reliably and systematically with low latency, less bandwidth, heterogeneity and maintaining the Quality of Service(QoS) befittingly.

2017

1. Service Based FOG Computing Model for IoT

   Ashrafi, Tasnia Heya, Hossain, Md. Arshad,  Arefin, Sayed Erfan, Das, Kowshik Dipta Jay, and Chakrabarty, Amitabha

   In 2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC) Oct 2017

   Abs

   The more we are heading towards the future with ever-growing number of IoT devices which is expected to take place in a giant number almost near trillions by 2020, the data access and computing are proceeding towards more complications and impediments requiring more efficient and logical data computation infrastructures. Cloud computing is a centralized Internet based computing model which acts like a storage as well as a network connection bridge between end devices and servers. Cloud computing has been ruling as a data computation model for quite a while but if we try to concentrate on the upcoming IoT generation, the vision will become a little bit blurry as it is not possible for the present cloud computing models to deal with such huge amount of data and to rescue from this foggy situation, Fog computing model comes forward. Instead of being a replacement of the cloud computing model, Fog computing model is an extension of Cloud which works as a distributed decentralized computing infrastructure in which data compute, storage and applications are distributed in the most logical, efficient place between the data source and the cloud. In this paper, we proposed an infrastructure with collaboration of Fog computing combined with Machine-to-Machine(M2M) intelligent communication protocol followed by integration of the Service Oriented Architecture(SOA) and this model will be able to transfer data by analyzing reliably and systematically with low latency, less bandwidth, heterogeneity in less amount of time maintaining the Quality of Service(QoS) befittingly.

2. Indoor localization system for assisting visually impaired people

   Alam, Md. Mazidul,  Arefin, Sayed Erfan, Alim, Miraj Al, Adib, Samiul Islam, and Rahman, Md. Abdur

   In 2017 International Conference on Electrical, Computer and Communication Engineering (ECCE) Oct 2017
3. Comparative analysis of computation models for IoT: Distributed fog vs. conventional cloud

   Heya, Tasnia Ashrafi,  Arefin, Sayed Erfan, Hossain, Md. Arshad, and Chakrabarty, Amitabha

   In 2017 4th International Conference on Advances in Electrical Engineering (ICAEE) Oct 2017
4. FOG Based Distributed IoT Infrastructure

   Ashrafi, Tasnia H., Arefin, Sayed E., Das, Kowshik D. J., Hossain, Md. A., and Chakrabarty, Amitabha

   In Proceedings of the Second International Conference on Internet of Things, Data and Cloud Computing Oct 2017

   Abs

   The Internet of Things(IoT) can be defined as a network connectivity bridge between people, systems and physical world. With the increasing number of IoT devices and networks, dealing with enormous number of data efficiently is becoming more and more challenging for the present infrastructure which is a very big matter of concern. In this paper, we depicted the current infrastructure and proposed another model of IoT infrastructure to surpass the difficulties of the existing infrastructure, which will be a coordinated effort of Fog computing amalgamation with Machine-to-Machine(M2M) intelligent communication protocol followed by incorporation of Service Oriented Architecture(SOA) and finally integration of Agent based SOA. This model will have the capacity to exchange data by breaking down dependably and methodically with low latency, less bandwidth, heterogeneity in less measure of time maintaining the Quality of Service(QoS) precisely.