Panagiotis Kintis

Advancing privacy-preserving AI is essential for building trustworthy and responsible intelligent systems. I am pleased to be a part of this NSF-supported workshop at Tennessee State University, bringing together leading researchers to explore secure learning and federated AI. This initiative will help strengthen interdisciplinary capacity in trustworthy AI.

15

Accepted papers for the Symposium on Usable Security and Privacy (USEC 2026) are now available: https://lnkd.in/gTzcPvf2 📈 Submissions up 65% 🎯 Acceptance rate 33% Encouraging signs for the continued growth and impact of usable security and privacy research.

39

*** New Research Publication *** Our research paper titled “Privacy-Preserving Unique, Robust, and Revocable Passcode Generation from Fingerprint Data” has been accepted for publication in Computers & Security (Elsevier) - a Rank #2 journal in the field of computer security and cryptography. Priyabrata Dash, Debasis Samanta, Monalisa Sarma, Ashok Kumar Das, and Athanasios V. Vasilakos. "Privacy Preserving Unique Robust and Revocable Passcode Generation from Fingerprint Data," in Computers & Security (Elsevier), October 2025, DOI: https://lnkd.in/dU4VUKCN. (2024 SCI Impact Factor: 5.4) This research explores how secure passcodes can be generated directly from fingerprint images, eliminating the need for traditional storage of biometric data. The study unfolds in three major stages: 1️) Fixed-length feature vector generation from fingerprint minutiae. 2️) Stable binary feature vector creation, ensuring robustness. 3️) Passcode generation with non-linkable and revocable properties — enhancing privacy and security. The approach ensures that even if a passcode is compromised, the original fingerprint cannot be reconstructed, preserving biometric privacy. The generated passcodes have wide-ranging potential - from secure identity generation and encryption key creation to remote authentication, data storage protection, and digital wallets. The proposed scheme is validated on FVC2002 and FVC2004 databases; the method achieved: * Genuine Acceptance Rates: 99.31% (FVC2002) and 99.25% (FVC2004) * False Acceptance Rate: 0% * Passcodes successfully passed NIST and Diehard randomness tests - confirming their cryptographic strength. A big thank you to my co-authors and collaborators: Priyabrata Dash (Advanced Technology Development Centre, IIT Kharagpur, India), Debasis Samanta (Department of Computer Science and Engineering, IIT Kharagpur, India) and Monalisa Sarma (Subir Chowdhury School of Quality and Reliability, IIT Kharagpur, India), and Athanasios Vasilakos (Center for AI Research (CAIR), University of Agder (UiA), 4879 Grimstad, Norway), for their valuable contributions! The full paper can be downloaded from Elsevier’s ScienceDirect: https://lnkd.in/dVtzTFUw #CyberSecurity #Biometrics #PrivacyPreserving #FingerprintRecognition #Research #ComputersAndSecurity #AcademicResearch #Security

64

3 Comments

Honored to have completed a peer review for an international conference paper on remote workforce security within a governance and control framework for #ICECET 2026, organized by the IEEE Italy Section and scheduled in Rome, Italy (6–9 July 2026). Istanbul Medipol University Operations Research Society and served as a Review Committee Member. The paper focused on strengthening security governance for distributed teams, aligning controls with organizational risk posture, compliance needs, and evolving remote work threats. Grateful for the opportunity to contribute to the review process of a multidisciplinary, peer‑reviewed IEEE conference that brings together global researchers and practitioners in electrical, computer, and energy technologies. Looking forward to more collaborations at the intersection of cybersecurity, remote work, and governance frameworks.

87

2 Comments

🚀 Proud to announce our latest publication in Scientific Reports—introducing a novel Federated Transfer Learning (FTL) framework for detecting rare and zero-day attack classes in Network Intrusion Detection Systems (NIDS)! 🔍 Why does it matter? Conventional models often struggle to identify rare and unseen cyberattacks due to limited, imbalanced data and privacy challenges. Our adaptive FTL approach leverages personalized client-side layers and transfer learning, enabling rapid detection and robust classification—even for zero-day threats—without compromising data privacy. 📊 Key results: Achieved state-of-the-art accuracy: CICIDS 2018: 98.90% UNSW-NB 15: 98.70% Edge-IIoT: 97.92% Outperformed existing FL-TL-CNN models by up to 4.21% on F1 score—especially for rare attack types. ✔️ What sets us apart? Personalized federated averaging for client-level adaptation Threshold-based detection & transfer learning for zero-day attacks Scalable, communication-efficient architecture 🛡️ The framework is benchmarked on CSE-CICIDS-2018, UNSW-NB15, and Edge-IIoT datasets. This sets a new standard for privacy-preserving and adaptive cybersecurity, ready for real-world deployment! 🤝 Kudos to our research team at VIT Chennai [Abhijit Chunduru, @Annie Jerusha] 🙏 Special thanks to Vijay Varadharajan, University of Newcastle, for his invaluable guidance, collaboration, and mentorship throughout this research journey. 🔗 Open Access article: https://rdcu.be/eISI1 #AI #FederatedLearning #Cybersecurity #NIDS #ZeroDayAttacks #Research #VITChennai #EdgeAI #TransferLearning #DeepLearning #ScientificReports

23

I’m pleased to share the abstract of Chapter 9 of my forthcoming authored volume "Machine Learning: Attacks, Defenses, and Emerging Strategies." The abstract is here: https://lnkd.in/gS8tJFjQ The chapter introduces a hybrid defense framework that combines adversarial training with a convolutional autoencoder-based preprocessing approach to enhance the robustness of deep image classifiers against FGSM and PGD attacks. Using the VGG16 model on MNIST and Fashion-MNIST datasets, the study shows that while adversarial perturbations can drastically reduce accuracy, from about 99% to below 6%, the proposed method restores it to around 88% and 70% respectively, all within sub-millisecond inference time. The work contributes to the growing research on adversarial robustness by bridging data-level and model-level defenses and outlining future directions toward scalable, real-time resilience in AI systems. #MachineLearning #AdversarialML #DeepLearning #ComputerVision #AI #Research #ImageClassification #AdversarialAttacks

30

Very pleased to share that the paper "Quantifying costs of enhanced security in multifactor authentication", co-authored with Seth Hastings, PhD, Neil Gandal, and Noa Barnir, was published in Information Systems Frontiers: https://lnkd.in/g5EFhKvU. We often hear about the importance of multi-factor authentication (MFA) to protect people and organizations. We completely agree! Nonetheless, there are real costs to adopting MFA. In addition to paying for the technology itself, MFA also introduces opportunity costs, from the extra time spent authenticating to the time legitimate users spend locked out if they cannot complete authentication. Through a collaboration with The University of Tulsa Office of IT, we inspected several years' worth of authentication logs. When the university switched over to a more onerous form of MFA (requiring a two-digit code through the mobile app in addition to biometrics), these opportunity costs shot way up, especially when using mobile devices. For full details, check out the paper! Pre-publication version available in case the article isn't available through your institution: https://lnkd.in/gtfm7MAb.

97

6 Comments

This is an interesting study which shows that old theories work interestingly in new contexts and how teams communicate really matters for addressing quality of requirements. Enjoy!

18