Banafsheh Saber Latibari
About
I am an Assistant Professor in the Department of Electrical and Computer Engineering at New Mexico State University.
Before joining NMSU, I was a Postdoctoral Research Associate in the ECE Department at the University of Arizona. I also served as an affiliate member of the Center for Semiconductor Manufacturing.
I completed my Ph.D. in Electrical and Computer Engineering at the University of California, Davis in 2024, with a dissertation on the small evolution of vision transformers for low-power devices. I hold an M.S. in Computer Engineering from Sharif University of Technology and a B.S. in Computer Engineering from K.N. Toosi University of Technology.
Education
Research Areas
Publications
10 journal articles, 20 conference papers, and 2 book chapters.
- 10.Stealthy Hardware Trojans in AI Accelerators: Attacks on Transformer, CNN, and Systolic ArchitecturesIEEE Micro
- 9.DDD-GenDT: Dynamic Data-driven Generative Digital Twin FrameworkIEEE Transactions on Artificial Intelligence, 2025
- 8.Autonomous Vehicle Security: Hybrid Threat Modeling ApproachIEEE Open Journal of Vehicular Technology, 2025
- 7.HWRiSe: AI-enabled Hardware Weakness Root Cause Analysis and Storytelling Framework with LLM-assisted Mitigation SuggestionTransactions on Design Automation of Electronic Systems, 2025
- 6.Optimizing Vision Transformers: Unveiling "Focus and Forget" for Enhanced Computational EfficiencyIEEE Access, 2025
- 5.Transformers: A Security PerspectiveIEEE Access, 2024
- 4.Cross-Core Data Sharing for Energy-Efficient GPUsACM Transactions on Architecture and Code Optimization, 2024
- 3.Optimized and Automated Secure IC Design Flow: A Defense-in-Depth ApproachIEEE Transactions on Circuits and Systems I (TCAS-I), 2024, Special Issue on Learning, Optimization, and Implementation for Circuits and Systems Driven by AI
- 2.Advanced Reinforcement Learning Solution for Clock Skew Engineering: Modified Q-Table Update Technique for Peak Current and IR Drop MinimizationIEEE Access, 2023
- 1.Hardware Trojan Detection using Machine Learning: A TutorialACM Transactions on Embedded Computing Systems, 2023
- 20.Semantic Smoothing via Novel View Synthesis for Robust SAR Image ClassificationACM Great Lakes Symposium on VLSI (GLSVLSI'26), Finger Lakes, NY, June 22–24, 2026
- 19.Lightweight SAR Ship Detection via Contrastive DistillationGLSVLSI'26, Finger Lakes, NY, June 22–24, 2026
- 18.Fine-Grained Patching via Contention Balancer: A Practical Mitigation Strategy for Spectre Vulnerabilities Using SpecScope Contention MapsInternational Symposium on Quality Electronic Design (ISQED'26), San Francisco, CA, April 8–10, 2026
- 17.Is Mamba Reliable for Medical Imaging?ISQED'26, San Francisco, CA, April 8–10, 2026
- 16.FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer ModelsIEEE International Conference on Computer Design (ICCD'25)
- 15.Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical ImagingICCD'25
- 14.RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented TutoringFrontiers in Education (FIE'25)
- 13.Integrating Generative AI into Cybersecurity Education: A Study of OCR and Multimodal LLM-assisted InstructionFIE'25
- 12.Joint Classification and Unknown Detection Using Class Conditional ProbabilityIEEE International Symposium on Signal & Systems (ISSCS'25)
- 11.Personalized Education with Generative AI and Digital Twins: VR, RAG and Zero-Shot Sentiment Analysis for Industry 4.0 Workforce DevelopmentAmerican Society for Engineering Education (ASEE'25)
- 10.Power Side-Channel Leakage Assessment of FPGA-Based Spiking Neural NetworksIEEE International Midwest Symposium on Circuits and Systems (MWSCAS'25), Lansing, MI, Aug 10–13, 2025
- 9.Transformers for Secure Hardware Systems: Applications, Challenges, and OutlookGLSVLSI'25, New Orleans, LA, June 30–July 2, 2025
- 8.Reliability of Capacitive Read in Arrays of Ferroelectric CapacitorsIEEE International Symposium on Circuits and Systems (ISCAS'25), London, UK, May 25–28, 2025
- 7.HLGM: A Novel Methodology for Improving Model Accuracy Using Saliency-Guided High and Low Gradient Masking14th International Conference on Information Science and Technology, Chengdu, China, Dec 6–9, 2024
- 6.IRET: Incremental Resolution Enhancing TransformerGLSVLSI'24, Tampa, FL, June 12–14, 2024
- 5.Automated Hardware Logic Obfuscation Framework Using GPTIEEE Dallas Circuits and Systems Conference (DCAS'24), Dallas, TX, April 19–21, 2024
- 4.Securing On-Chip Learning: Navigating Vulnerabilities and Potential Safeguards in Spiking Neural Network ArchitecturesISCAS'24, Singapore, May 19–22, 2024
- 3.A Survey on FHE AccelerationDCAS'23, Dallas, TX, April 19–21, 2023
- 2.RAPTA: A Hierarchical Representation Learning Solution for Real-Time Prediction of Path-Based Static Timing AnalysisGLSVLSI'22, Irvine, CA, June 6–8, 2022
- 1.Adaptive-Gravity: A Defense Against Adversarial Samples23rd International Symposium on Quality Electronic Design (ISQED'22), San Francisco, CA, April 23–25, 2022
- 2.Generative AI in Higher Education Assessment: Theory, Practice, and Ethical Implications (Part II.3)Springer, 2026
- 1.Machine Learning Techniques for Detecting Hardware Trojans in ASIC Designs (Chapter 4)In Advances in Hardware Design for Security and Trust, CRC Press, 2025
Teaching
EE 526/462 Computer System Architecture Fall 2026
Students & Mentoring
Building the CORTEX Lab, Computing for Optimized, Reliable, and Trustworthy Edge eXecution, at NMSU. Ph.D., M.S., and undergraduate students interested in joining are welcome to reach out.
News
Joined New Mexico State University as Assistant Professor in the Department of Electrical and Computer Engineering.
Two papers accepted to the ACM Great Lakes Symposium on VLSI (GLSVLSI'26), Finger Lakes, NY.
Two papers accepted to the International Symposium on Quality Electronic Design (ISQED'26), San Francisco, CA. Served as Session Chair.
Appointed Guest Editor for a Special Issue of MDPI Sensors.
Served as Session Chair for the Network and Distributed System Security (NDSS) Symposium, San Diego, CA.
Two papers accepted to the IEEE International Conference on Computer Design (ICCD'25), Dallas, TX.