Sumit Kumar Jha

Eminent Scholar Chair Professor of Computer Science

prof_pic.jpg

384 CASE Building

11200 SW 8th Street

Miami, FL 33199

Prof. Jha’s research interests lie in the following areas:

  • Artificial Intelligence
  • Logic and Automata Theory
  • Quantum Computing
  • Emerging Architectures

Principal Investigator for $17 million in awarded projects since 2014, including DARPA GARD, AFRL ML-RCP, ONR Science of AI, Department of Energy EXPRESS, NSF Scalable Parallelism in the Extreme (SPX), NSF Software and Hardware Foundations (SHF), NSF Formal Methods in the Field (FMitF), NSF Secure and Trustworthy Computing (SaTC), National Nuclear Security Administration (NNSA), Department of Energy (DOE) ASCR RENEW, and AFOSR Young Investigator Program.

news

Sep 27, 2024 DAIR.AI listed our work on jailbreaking LLMs as one of the top 10 ML Papers of the Week!
Feb 11, 2024 Three (3) papers have been accepted at the ACM Design Automation Conference (DAC) 2024!

selected publications

  1. Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision
    C. Walker, SK Jha, S. Chen, and R. Ewetz
    Proceedings of the 38th AAAI International Conference on Artificial Intelligence (AAAI), 2024
    PDF
  2. Jailbreaking Large Language Models with Symbolic Mathematics
    E. Bethany, M. Bethany, J.A. Nolazco Flores, SK Jha, and P. Najafirad
    Workshop on Socially Responsible Language Modelling Research (SoLaR) at NeurIPS, 2024
  3. AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
    A. Nunez, NT. Islam, SK Jha, and P. Najafirad
    The First Workshop on Safe & Trustworthy Agents (SATA) at NeurIPS, 2024
  4. On the Design of Novel Attention Mechanism for Enhanced Efficiency of Transformers
    SK Jha, S. Jha, R. Ewetz, and A. Velasquez
    61st ACM Design Automation Conference (DAC), 2024
  5. Exploring the Predictive Capabilities of AlphaFold Using Adversarial Protein Sequences
    I. Alkhouri, SK Jha, R. Ewetz, S. Jha, and A. Velasquez
    IEEE Transactions on Artificial Intelligence (IEEE TAI), 2024
  6. Counterexample Guided Inductive Synthesis Using Large Language Models and Satisfiability Solving
    SK Jha, S. Jha, P. Lincoln, ND. Bastian, A. Velasquez, R. Ewetz, and 1 more author
    IEEE Military Communications Conference (MILCOM), 2023
    BEST PAPER CANDIDATE
    PDF
  7. Automated Synthesis for In-Memory Computing
    M. Rashed, S. Thijssen, SK Jha, and R. Ewetz
    42nd International Conference on Computer-Aided Design (ICCAD), 2023
    PDF
  8. UpTime: Towards Flow-Based In-Memory Computing with High Fault-Tolerance
    S. Thijssen, M. Rashed, SK Jha, and R. Ewetz
    60th Design Automation Conference (DAC), 2023
    PDF
  9. Logic Synthesis for Digital In-Memory Computing
    M. Rashed, SK Jha, and R. Ewetz
    41st International Conference on Computer-Aided Design (ICCAD), 2022
    BEST PAPER CANDIDATE
    PDF
  10. Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations
    SK Jha, A. Velasquez, A. Ramanathan, and S. Jha
    36th AAAI International Conference on Artificial Intelligence (AAAI), 2022
    Oral Presentation
    PDF
  11. PATH: Evaluation of Boolean Logic using Path-based In-Memory Computing
    S. Thijssen, SK Jha, and R. Ewetz
    59th Design Automation Conference (DAC), 2022
    PDF
  12. Towards Resilient Analog In-Memory Deep Learning via Data Layout Re-Organization
    M. Rashed, A. Awad, SK Jha, and R. Ewetz
    59th Design Automation Conference (DAC), 2022
    PDF
  13. On Smoother Attributions using Neural Stochastic Differential Equations
    SK Jha, R. Ewetz, A. Velasquez, and S. Jha
    30th International Joint Conference on Artificial Intelligence (IJCAI), 2021
    PDF
  14. Hybrid Analog-Digital In-Memory Computing
    M. Rashed, SK Jha, and R. Ewetz
    International Conference on Computer-Aided Design (ICCAD), 2021
    PDF
  15. COMPACT: Flow-Based Computing on Nanoscale Crossbars with Minimal Semiperimeter
    S. Thijssen, SK Jha, and R. Ewetz
    Design Automation and Test in Europe (DATE), 2021
    BEST PAPER CANDIDATE
    PDF
  16. DP-MAP: Towards Resistive Dot-Product Engines with Improved Precision
    N. Uysal, B. Zhang, SK Jha, and R. Ewetz
    International Conference on Computer-Aided Design (ICCAD), 2020
    PDF
  17. Attribution-Based Confidence Metric for Deep Neural Networks
    S. Jha, S. Raj, SL Fernandes, SK Jha, B. Jalaian, G. Verma, and 1 more author
    Advances in Neural Information Processing Systems (NeurIPS), 2019
    PDF