Seetal Potluri

Works (8)

Updated: March 12th, 2024 05:01

2023 article

Scalable Scan-Chain-Based Extraction of Neural Network Models

2023 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION, DATE.

By: S. Jiang *, S. Potluri n & T. Ho *

author keywords: Deep neural network; testing; scan-chain; model extraction; scalability
TL;DR: The results show that the method outperforms the scan-chain attack proposed in ICCAD 2021 by an average increase in the extracted neural network's functional accuracy and 2–3 orders of reduction in queries, and it is demonstrated that the attack is highly effective even in the presence of countermeasures against adversarial samples. (via Semantic Scholar)
UN Sustainable Development Goals Color Wheel
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: March 11, 2024

2022 journal article

SeqL plus : Secure Scan-Obfuscation With Theoretical and Empirical Validation

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 42(5), 1406–1410.

By: S. Potluri n, S. Kundu *, A. Kumar *, K. Basu * & A. Aysu n

author keywords: Flip-flops; Logic gates; Security; Complexity theory; Resists; Resilience; Iterative algorithms; IP piracy; scan-chains; scan-scrambling
TL;DR: This study reveals the first formulation and complexity analysis of Boolean satisfiability (SAT)-based attack on scan-scrambling and proposes an iterative swapping-based scan-cell scrambling algorithm to defeat SAT-based attack. (via Semantic Scholar)
UN Sustainable Development Goals Color Wheel
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: June 5, 2023

2022 article

Towards AI-Enabled Hardware Security: Challenges and Opportunities

2022 IEEE 28TH INTERNATIONAL SYMPOSIUM ON ON-LINE TESTING AND ROBUST SYSTEM DESIGN (IOLTS 2022).

By: H. Sayadi *, M. Aliasgari *, F. Aydin n, S. Potluri n, A. Aysu n, J. Edmonds*, S. Tehranipoor *

TL;DR: The growing role of AI/ML techniques in hardware and architecture security field is highlighted and insightful discussions on pressing challenges, opportunities, and future directions of designing accurate and efficient machine learning-based attacks and defense mechanisms in response to emerging hardware security vulnerabilities in modern computer systems and next generation of cryptosystems are provided. (via Semantic Scholar)
Source: Web Of Science
Added: October 24, 2022

2021 article

Stealing Neural Network Models through the Scan Chain: A New Threat for ML Hardware

2021 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN (ICCAD).

By: S. Potluri n & A. Aysu n

TL;DR: This paper shows a new style of attack, for the first time, on ML models running on embedded devices by abusing the scan-chain infrastructure, and outperforms mathematical model extraction proposed in CRYPTO 2020, USENIX 2020, and ICML 2020. (via Semantic Scholar)
UN Sustainable Development Goals Color Wheel
UN Sustainable Development Goal Categories
9. Industry, Innovation and Infrastructure (OpenAlex)
Source: Web Of Science
Added: February 21, 2022

2021 article

iTimed: Cache Attacks on the Apple A10 Fusion SoC

2021 IEEE INTERNATIONAL SYMPOSIUM ON HARDWARE ORIENTED SECURITY AND TRUST (HOST), pp. 80–90.

By: G. Haas n, S. Potluri n & A. Aysu n

TL;DR: It is found that the first cache timing side-channel attack on one of Apple's mobile devices can reduce the security of OpenSSL AES-128 by 50 more bits than a straightforward adaptation of PRIME+PROBE, while requiring only half as many side channel measurement traces. (via Semantic Scholar)
Source: Web Of Science
Added: June 13, 2022

2020 journal article

2Deep: Enhancing Side-Channel Attacks on Lattice-Based Key-Exchange via 2-D Deep Learning

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 40(6), 1217–1229.

By: P. Kashyap n , F. Aydin n, S. Potluri n, P. Franzon n  & A. Aysu n

author keywords: Resistance; Performance evaluation; Deep learning; Protocols; Power measurement; Side-channel attacks; NIST; Cross-device; data-augmentation; deep learning (DL); lattice-based key-exchange protocols; power side channels
TL;DR: 2Deep—a deep-learning (DL)-based SCA—targeting parallelized implementations of PQKE protocols, namely, Frodo and NewHope with data augmentation techniques are proposed, exploring approaches that convert 1-D time-series power measurement data into 2-D images to formulate SCA an image recognition task. (via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries, ORCID
Added: June 10, 2021

2020 article

Machine Learning and Hardware security: Challenges and Opportunities -Invited Talk

2020 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED-DESIGN (ICCAD).

By: F. Regazzoni *, S. Bhasin *, A. Pour*, I. Alshaer *, F. Aydin n, A. Aysu n, V. Beroulle *, G. Di Natale * ...

author keywords: machine learning; hardware security
TL;DR: Novel applications of machine learning for hardware security, such as evaluation of post quantum cryptography hardware and extraction of physically unclonable functions from neural networks and practical model extraction attack based on electromagnetic side-channel measurements are demonstrated. (via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries
Added: August 30, 2021

2020 journal article

Security of Microfluidic Biochip: Practical Attacks and Countermeasures

ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 25(3).

By: H. Chen *, S. Potluri n & F. Koushanfar *

author keywords: Microfluidic biochip; security; hardware Trojans; hardware obfuscation; camouflaging; Trojan detection
TL;DR: This article proposes a systematic framework for applying Reverse Engineering (RE) attacks and Hardware Trojan (HT) attacks on MFBs as well as for practical countermeasures against the proposed attacks. (via Semantic Scholar)
UN Sustainable Development Goals Color Wheel
UN Sustainable Development Goal Categories
Source: Web Of Science
Added: November 16, 2020

Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.

Certain data included herein are derived from the Web of Science© and InCites© (2025) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.