Debopriya Roy Dipta

Debopriya Roy Dipta

he/him

Assistant Professor | Electrical & Computer Engineering

Posts by Collection

portfolio

publications

Dynamic Time Warping Assisted SVM Classifier for Bangla Speech Recognition

Published in 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), 2018

We propose a Bangla speech recognition system that combines Dynamic Time Warping (DTW) for feature alignment with a Support Vector Machine (SVM) classifier, achieving robust recognition performance on a collected Bangla speech dataset.

Recommended citation: M. M. Rahman, D. R. Dipta and M. M. Hasan, "Dynamic Time Warping Assisted SVM Classifier for Bangla Speech Recognition," 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh, 2018.

Efficient Hardware Implementation of 256-bit ECC Processor Over Prime Field

Published in 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), 2019

We present an efficient FPGA-based hardware implementation of a 256-bit Elliptic Curve Cryptography (ECC) processor optimized for speed and area over prime fields.

Recommended citation: M. S. Rahman, M. S. Hossain, E. H. Rahat, D. R. Dipta, H. M. R. Faruque and F. K. Fattah, "Efficient Hardware Implementation of 256-bit ECC Processor Over Prime Field," 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), Bangladesh, 2019.

Design of a Convolutional Neural Network Based Smart Waste Disposal System

Published in 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019

We design a smart waste disposal system using a convolutional neural network to automatically classify and sort waste materials, enabling automated recycling and reducing manual sorting effort.

Recommended citation: M. S. Haque Sunny, D. R. Dipta, S. Hossain, H. M. Resalat Faruque and E. Hossain, "Design of a Convolutional Neural Network Based Smart Waste Disposal System," 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh, 2019.

Comparison of Different Hybrid Renewable Energy Systems With Optimized PV Configuration to Realize the Effects of Multiple Schemes

Published in 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019

We compare different hybrid renewable energy system configurations with optimized photovoltaic setups to evaluate performance trade-offs and the effects of various integration schemes on energy yield and reliability.

Recommended citation: F. I. Bappy, M. Jahirul Islam, A. K. Podder, D. R. Dipta, H. M. Resalat Faruque and E. Hossain, "Comparison of Different Hybrid Renewable Energy Systems With Optimized PV Configuration to Realize the Effects of Multiple Schemes," 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh, 2019.

A Comprehensive Review of the Load Forecasting Techniques Using Single and Hybrid Predictive Models

Published in IEEE Access, 2020

A comprehensive survey of electrical load forecasting methods, covering statistical models, machine learning approaches, and hybrid techniques, with comparative analysis of their accuracy, computational requirements, and applicability across forecasting horizons.

Recommended citation: A. A. Mamun, M. Sohel, N. Mohammad, M. S. Haque Sunny, D. R. Dipta and E. Hossain, "A Comprehensive Review of the Load Forecasting Techniques Using Single and Hybrid Predictive Models," IEEE Access, vol. 8, pp. 134911-134939, 2020.

Metrics and Enhancement Strategies for Grid Resilience and Reliability during Natural Disasters

Published in Applied Energy, 2021

We review and propose quantitative metrics for assessing electrical grid resilience and reliability under natural disaster conditions, and evaluate enhancement strategies including microgrids, distributed energy resources, and advanced communication systems.

Recommended citation: E. Hossain, S. Roy, N. Mohammad, N. Nawar, D. R. Dipta, "Metrics and enhancement strategies for grid resilience and reliability during natural disasters," Applied Energy, Volume 290, 2021.

Solar Energy in the United States: Development, Challenges and Future Prospects

Published in Energies, 2021

A comprehensive review of solar energy development in the United States, examining installation trends, policy challenges, grid integration issues, and future prospects for utility-scale and distributed solar deployment.

Recommended citation: S. Tabassum, T. Rahman, A. U. Islam, S. Rahman, D. R. Dipta, S. Roy, N. Mohammad, N. Nawar, E. Hossain, "Solar Energy in the United States: Development, Challenges and Future Prospects," Energies, 14(23), Article 8142, 2021.

DF-SCA: Dynamic Frequency Side Channel Attacks are Practical

Published in Proceedings of the 38th Annual Computer Security Applications Conference (ACSAC '22), 2022

We show that CPU core frequency values, readable by unprivileged users through the cpufreq interface, form a practical side channel on Linux and Android for website fingerprinting, keystroke detection, and password inference.

Recommended citation: D. R. Dipta and Berk Gulmezoglu, "DF-SCA: Dynamic Frequency Side Channel Attacks are Practical," Proceedings of the 38th Annual Computer Security Applications Conference (ACSAC '22), Association for Computing Machinery, New York, NY, USA, 841–853, 2022.
Download Paper

MAD-EN: Microarchitectural Attack Detection Through System-Wide Energy Consumption

Published in IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023

MAD-EN detects microarchitectural attacks such as Spectre and Meltdown from system-wide energy consumption traces collected with Intel RAPL, with 69.3% lower performance overhead than performance counter-based detection.

Recommended citation: D. R. Dipta and B. Gulmezoglu, "MAD-EN: Microarchitectural Attack Detection Through System-Wide Energy Consumption," IEEE Transactions on Information Forensics and Security (IEEE TIFS), vol. 18, pp. 3006-3017, 2023.
Download Paper

DefWeb: Defending User Privacy against Cache-based Website Fingerprinting Attacks with Intelligent Noise Injection

Published in Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC '23), 2023

DefWeb is a generative-learning defense against cache-based website fingerprinting that injects minimal, targeted noise during page rendering through self-modifying code, cutting attacker accuracy to 28.8% on real systems with 9.5% overhead.

Recommended citation: S. Son, D. R. Dipta and B. Gulmezoglu, "DefWeb: Defending User Privacy against Cache-based Website Fingerprinting Attacks with Intelligent Noise Injection," Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC '23), Association for Computing Machinery, New York, NY, USA, 379–393, 2023.
Download Paper

Dynamic Frequency-Based Fingerprinting Attacks against Modern Sandbox Environments

Published in 2024 IEEE 9th European Symposium on Security and Privacy (EuroS&P), 2024

We show that CPU frequency reporting sensors on Intel and AMD processors, readable from user space, let an attacker fingerprint Docker containers and workloads inside sandboxes such as gVisor, AWS Firecracker, Gramine-SGX, and AMD SEV.

Recommended citation: D. R. Dipta, T. Tiemann, B. Gulmezoglu, E. Marin and T. Eisenbarth, "Dynamic Frequency-Based Fingerprinting Attacks against Modern Sandbox Environments," 2024 IEEE 9th European Symposium on Security and Privacy (EuroS&P), pp. 327-344, Vienna, Austria, 2024.
Download Paper

Systematical Evasion From Learning-Based Microarchitectural Attack Detection Tools

Published in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (IEEE JETCAS), 2024

We build a fuzzing framework that manipulates hardware performance counter values in a controlled way and use it to modify attack code so that it evades learning-based microarchitectural attack detectors.

Recommended citation: D. R. Dipta, J. Tan and B. Gulmezoglu, "Systematical Evasion From Learning-Based Microarchitectural Attack Detection Tools," IEEE Journal on Emerging and Selected Topics in Circuits and Systems (IEEE JETCAS), vol. 14, no. 4, pp. 823-833, Dec. 2024.
Download Paper

DimShield: Exploring Intrinsic Dimension Estimation for Enhanced Machine Learning Security

Published in In preparation, 2025

DimShield is a runtime defense framework that uses intrinsic dimension estimation to protect deep neural networks against adversarial attacks.

Recommended citation: D. R. Dipta, K. Christofferson, S. Son and B. Gulmezoglu, "DimShield: Exploring Intrinsic Dimension Estimation for Enhanced Machine Learning Security." In preparation.

Exploiting and Mitigating Information Leakage at the Container-Kernel Interface

Published in In preparation, 2025

We study information leakage at the interface between containers and the shared Linux kernel, and propose mitigations.

Recommended citation: D. R. Dipta, E. Marin, B. Gulmezoglu and T. Eisenbarth, "Exploiting and Mitigating Information Leakage at the Container-Kernel Interface." In preparation.

uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs

Published in arXiv preprint arXiv:2605.15503, 2026

We find that LLMs frequently misplace or misuse critical attack primitives when writing microarchitectural attack code, and present uGen, a retrieval-augmented, multi-agent framework that supplies the missing domain knowledge to generate working proof-of-concepts.

Recommended citation: D. R. Dipta, T. Tiemann, E. Marin, T. Eisenbarth and B. Gulmezoglu, "uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs," arXiv preprint arXiv:2605.15503, 2026.
Download Paper

talks

DF-SCA: Dynamic Frequency Side Channel Attacks are Practical

Published:

Invited talk at NVIDIA presenting “DF-SCA: Dynamic Frequency Side Channel Attacks are Practical,” which shows that CPU frequency values readable by unprivileged users enable website fingerprinting and keystroke inference.

DF-SCA: Dynamic Frequency Side Channel Attacks are Practical

Published:

Conference presentation at ACSAC 2022, presenting the paper “DF-SCA: Dynamic Frequency Side Channel Attacks are Practical.” The talk introduced the dynamic frequency side channel, demonstrated its practicality for keystroke inference and website fingerprinting across unprivileged settings, and discussed implications across Intel, AMD, and ARM platforms.

Dynamic Frequency-Based Fingerprinting Attacks against Modern Sandbox Environments

Published:

Conference presentation at IEEE EuroS&P 2024, presenting the paper “Dynamic Frequency-Based Fingerprinting Attacks against Modern Sandbox Environments.” The talk showed how CPU frequency reporting sensors readable from user space on Intel and AMD processors let an attacker fingerprint Docker containers and workloads running inside gVisor, AWS Firecracker, Gramine-SGX, and AMD SEV, and presented a noise-injection countermeasure.

DF-SCA: Dynamic Frequency Side Channel Attacks are Practical

Published:

Poster presentation at the Youth Cyber Summit organized by the Iowa Cyber Hub, engaging high school and undergraduate students in understanding how hardware-level side-channel attacks work and why they matter for real-world security.

DF-SCA: Dynamic Frequency Side Channel Attacks are Practical

Published:

Poster presentation at the CEAB event organized by the Iowa Cyber Hub, demonstrating the practical implications of dynamic frequency side-channel attacks and highlighting the need for hardware-aware security practices.

Exploiting Dynamic Frequency: Side-Channel Attacks and Evasion in Modern Systems

Published:

Invited talk covering the dynamic frequency side-channel attack (DF-SCA) paradigm, its extension to fingerprinting modern sandbox environments, and systematic techniques for evading machine learning-based microarchitectural attack detectors. The talk also discussed ongoing work on LLM-assisted security evaluation frameworks.

teaching

Senior Design Project Mentor — CPR E 491/492

Senior Design Mentorship, Iowa State University, Department of Electrical and Computer Engineering, 2022

Courses: CPR E 491 (Senior Design Project I) — Fall 2022; CPR E 492 (Senior Design Project II) — Spring 2023