Peer-Reviewed Publications ( in Reverse Chronological Order )

  1. Calibration and Correctness of Language Models for Code
    Spiess, Claudio, David Gros, Kunal Suresh Pai, Michael Pradel, Md Rafiqul Islam Rabin, Amin Alipour, Susmit Jha, Prem Devanbu, and Toufique Ahmed
    IEEE/ACM 47th International Conference on Software Engineering (ICSE), 2025

  2. Zero-shot Detection of Out-of-Context Objects Using Foundation Models
    Anirban Roy, Adam Cobb, Ramneet Kaur, Sumit Jha, Nathaniel Bastian, Alexander Berenbeim, and Robert Thomson, Iain Cruickshank, Alvaro Velasquez, Susmit Jha
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

  3. Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
    Ramneet Kaur, Colin Samplawski, Adam D. Cobb, Anirban Roy, Brian Matejek, Manoj Acharya, Daniel Elenius, Alexander Michael Berenbeim, John A. Pavlik, Nathaniel D. Bastian, Susmit Jha
    Safe Generative AI Workshop @ NeurIPS 2024

  4. Investigating LLM Memorization: Bridging Trojan Detection and Training Data Extraction
    Manoj Acharya, Xiao Lin, Susmit Jha
    Safe Generative AI Workshop @ NeurIPS 2024

  5. Enhancing Semantic Clustering for Uncertainty Quantification & Conformal Prediction by LLMs
    Ramneet Kaur, Colin Samplawski, Adam D. Cobb, Anirban Roy, Brian Matejek, Manoj Acharya, Daniel Elenius, Alexander Michael Berenbeim, John A. Pavlik, Nathaniel D. Bastian, Susmit Jha
    Workshop on Statistical Frontiers in LLMs and Foundation Models @ NeurIPS 2024

  6. Second-Order Forward-Mode Automatic Differentiation for Optimization
    Adam D. Cobb, Atilim Gunes Baydin, Barak A. Pearlmutter, Susmit Jha
    16th International OPT Workshop on Optimization for Machine Learning @ NeurIPS 2024

  7. SpikingVTG: Saliency Feedback Gating Enabled Spiking Video Temporal Grounding
    Malyaban Bal, Brian Matejek, Susmit Jha, Adam D. Cobb
    Machine Learning and Compression Workshop @ NeurIPS 2024

  8. Post-hoc Uncertainty Quantification for Neurosymbolic Artificial Intelligence
    Berenbeim, Alexander, Ramneet Kaur, Adam D. Cobb, Anirban Roy, Susmit Jha, and Nathaniel D. Bastian
    IEEE Military Communications Conference (MILCOM), 2024

  9. Co-synthesis of code and formal models using large language models and functors
    Jha, Sumit Kumar, Susmit Jha, Rickard Ewetz, and Alvaro Velasquez.
    IEEE Military Communications Conference (MILCOM), 2024

  10. Shrinking POMCP: A Framework for Real-Time UAV Search and Rescue
    Zhang, Y., Luo, B., Mukhopadhyay, A., Stojcsics, D., Elenius, D., Roy, A., Jha, S., Maroti, M., Koutsoukos, X., Karsai, G. and Dubey, A.,
    International Conference on Assured Autonomy (ICAA), 2024

  11. Co-synthesis of code and formal models using large language models and functors.
    Jha, Sumit Kumar, Susmit Jha, Rickard Ewetz, and Alvaro Velasquez
    International Conference on Assured Autonomy (ICAA), 2024

  12. Neuro-symbolic Generative AI Assistant for System Design
    Jha, Susmit, Sumit Kumar Jha, and Alvaro Velasquez
    22nd ACM-IEEE International Symposium on Formal Methods and Models for System Design (MEMOCODE), 2024

  13. Automated Synthesis of Hardware Designs using Symbolic Feedback and Grammar-Constrained Decoding in Large Language Models
    Jha, Sumit Kumar, Susmit Jha, Muhammad Rashedul Haq Rashed, Rickard Ewetz, and Alvaro Velasquez
    NAECON 2024 IEEE National Aerospace and Electronics Conference

  14. On the Design of Novel Attention Mechanism for Enhanced Efficiency of Transformers
    Sumit Kumar Jha, Susmit Jha, Rickard Ewetz, and Alvaro Velasquez
    61st ACM/IEEE Design Automation Conference (DAC '24)

  15. TrinityAI: towards trustworthy, resilient, and interpretable AI for high-assurance applications
    Susmit Jha
    Assurance and Security for AI-enabled Systems, SPIE, 2024

  16. Bayesian graph representation learning for adversarial patch detection
    Berenbeim, Alexander M., Alexander V. Wei, Adam Cobb, Anirban Roy, Susmit Jha, and Nathaniel D. Bastian
    Assurance and Security for AI-enabled Systems, SPIE, 2024

  17. Safeguarding Network Intrusion Detection Models from Zero-day Attacks and Concept Drift
    Matejek, Brian, Ashish Gehani, Nathaniel D. Bastian, Daniel Clouse, Bradford Kline, and Susmit Jha
    AAAI Workshop on Artificial Intelligence for Cyber Security (AICS) 2024

  18. Exploring The Predictive Capabilities of AlphaFold Using Adversarial Protein Sequences.
    Alkhouri, Ismail R., Sumit Jha, Andre Beckus, George Atia, Susmit Jha, Rickard Ewetz, and Alvaro Velasquez.
    IEEE Transactions on Artificial Intelligence 2024
    Paper (PDF)

  19. Task-agnostic detector for insertion-based backdoor attacks
    Lyu, Weimin, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, and Chao Chen
    NAACL Findings, 2024
    Paper (PDF)

  20. Concept-based Analysis of Neural Networks via Vision-Language Models
    Ravi Mangal, Nina Narodytska, Divya Gopinath, Boyue Caroline Hu, Anirban Roy, Susmit Jha, and Corina Pasareanu
    7th Symposium on AI Verification 2024
    Paper (PDF)

  21. Direct Amortized Likelihood Ratio Estimation
    Adam Cobb, Brian Matejek, Daniel Elenius, Anirban Roy, Susmit Jha:
    38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024
    Paper (PDF)

  22. Principled Out-of-Distribution Detection via Multiple Testing
    Akshayaa Magesh, Venugopal V. Veeravalli, Anirban Roy, Susmit Jha
    Journal of Machine Learning Research, 2023
    Paper (PDF)

  23. AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
    Adam D. Cobb, Anirban Roy, Daniel Elenius, Frederick Michael Heim, Brian Swenson, Sydney Whittington, James D Walker, Theodore Bapty, Joseph Hite, Karthik Ramani, Christopher McComb, Susmit Jha
    Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 (Benchmarks and Datasets)
    Paper (PDF)

  24. Direct Amortized Likelihood Ratio Estimation
    Adam D. Cobb, Brian Matejek, Daniel Elenius, Anirban Roy, Susmit Jha
    NeurIPS workshop on Machine Learning and the Physical Sciences, 2023
    Paper (PDF)

  25. Universal Trojan Signatures in Reinforcement Learning
    Manoj Acharya, Weichao Zhou, Anirban Roy, Xiao Lin, Wenchao Li, Susmit Jha
    NeurIPS Workshop on Backdoors in Deep Learning, 2023
    Paper (PDF)

  26. TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models
    Indranil Sur, Karan Sikka, Matt Walmer, Kaushik Koneripalli, Anirban Roy, Xiao Lin, Ajay Divakaran, Susmit Jha
    International Conference on Computer Vision (ICCV) 2023
    Paper (PDF)

  27. Counterexample Guided Inductive Synthesis Using Large Language Models and Satisfiability Solving
    Sumit Jha, Susmit Jha, Pat Lincoln, Nate D. Bastian, Alvaro Velasquez, Rickard Ewetz, Sandeep Neema
    IEEE Military Communications Conference (MILCOM) 2023
    Paper (PDF)

  28. Neural SDEs for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions
    Sumit Jha, Susmit Jha, Rickard Ewetz, Alvaro Velasquez
    IEEE Military Communications Conference (MILCOM) 2023
    Paper (PDF)

  29. Dehallucinating Large Language Models Using Formal Methods Guided Iterative Prompting
    Susmit Jha, Sumit Jha, Pat Lincoln, Nate D. Bastian, Alvaro Velasquez, Sandeep Neema
    IEEE International Conference on Assured Autonomy (ICAA) 2023
    Paper (PDF)

  30. Predicting Out-of-Distribution Performance of Deep Neural Networks Using Model Conformance
    Ramneet Kaur, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee
    IEEE International Conference on Assured Autonomy (ICAA) 2023
    Paper (PDF)

  31. Detecting Trojaned DNNs using counterfactual attributions
    Karan Sikka, Indranil Sur, Anirban Roy, Ajay Divakaran, Susmit Jha
    IEEE International Conference on Assured Autonomy (ICAA) 2023
    Paper (PDF)

  32. Principled OOD Detection via Multiple Testing
    Askhayaa Magesh, Venu V Veeravalli, Susmit Jha, Anirban Roy
    IEEE International Symposium on Information Theory 2023
    Paper (PDF)

  33. CODiT: Conformal Out-of-Distribution Detection in Time-Series Data for Cyber-Physical Systems.
    Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Yahan Yang, Susmit Jha, Anirban Roy, Oleg Sokolsky, and Insup Lee.
    ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)
    Paper (PDF) Code

  34. Characterizing the 1s:E state in the 28-Si:77-Se+ spin-photon system by the equation-of-motion variational quantum eigensolver method
    Cody Fan, Adam Cobb, Murat Sarihan, Jiahui Huang, Jin Ho Kang, Khalifa Azizur-Rahman, Susmit Jha, Chee Wei Wong
    Bulletin of the American Physical Society
    Paper (PDF)

  35. Responsible Reasoning with Large Language Models and the Impact of Proper Nouns.
    Sumit Jha, Rickard Ewetz, Alvaro Velasquez, and Susmit Jha.
    Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022
    Paper (PDF)

  36. Principal Manifold Flows.
    Edmond Cunningham, Adam Cobb, Susmit Jha
    39th International Conference on Machine Learning (ICML), 2022.
    Paper (PDF)

  37. Dual-Key Multimodal Backdoors for Visual Question Answering.
    Walmer, Matthew, Karan Sikka, Indranil Sur, Abhinav Shrivastava, and Susmit Jha
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2022.
    Paper (PDF)

  38. Detecting out-of-context objects using graph contextual reasoning network.
    Manoj Acharya, Anirban Roy, Kaushik Koneripalli, Susmit Jha, Christopher Kanan, Ajay Divakaran
    31st International Joint Conference on Artificial Intelligence (IJCAI), 2022.
    Paper (PDF)

  39. Trigger Hunting with a Topological Prior for Trojan Detection.
    Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao, Susmit Jha, Chao Chen
    10th International Conference on Learning Representations (ICLR), 2022.
    Paper (PDF)

  40. Runtime monitoring of deep neural networks using top-down context models inspired by predictive processing and dual process theory.
    Anirban Roy, Adam Cobb, Nathaniel Bastian, Brian Jalaian, and Susmit Jha
    AAAI Spring Symposium 2022.
    Paper (PDF)

  41. Context-aware Collaborative Neuro-Symbolic Inference in IoBTs.
    Tarek Abdelzaher, Nathaniel D. Bastian, Susmit Jha, Lance Kaplan, Mani Srivastava, and Venugopal V. Veeravalli.
    IEEE Military Communications Conference (MILCOM), IEEE, 2022.
    Paper (PDF)

  42. iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
    Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Edgar Dobriban, Oleg Sokolsky, Insup Lee
    36th AAAI Conference on Artificial Intelligence (AAAI), 2022
    Paper (PDF)

  43. Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations
    Sumit Jha, Rickard Ewetz, Alvaro Velasquez, Arvind Ramanathan, Susmit Jha
    36th AAAI Conference on Artificial Intelligence (AAAI), 2022
    Paper (PDF)

  44. On Diverse System-Level Design Using Manifold Learning and Partial Simulated Annealing.
    Cobb, Adam, Anirban Roy, Daniel Elenius, Kaushik Koneripalli, and Susmit Jha.
    Proceedings of the Design Society 2: 1541-1548, 2022 Top 10% Paper Award
    Paper (PDF)

  45. Trinity AI Co-Designer for Hierarchical Oracle-guided Design of Cyber-Physical Systems
    Adam Cobb, Anirban Roy, Daniel Elenius, and Susmit Jha.
    IEEE Workshop on Design Automation for CPS and IoT (DESTION), 2022
    Paper (PDF)

  46. Principles of Robust Learning and Inference for IoBTs
    Nathaniel D Bastian, Susmit Jha, Paulo Tabuada, Venugopal Veeravalli, Gunjan Verma
    Book: IoT for Defense and National Security
    Paper (PDF)

  47. On Detection of Out of Distribution Inputs in Deep Neural Networks
    Susmit Jha, Anirban Roy
    IEEE 3rd International Conference on Cognitive Machine Intelligence (CogMI), 2021
    Paper (PDF)

  48. On Smoother Attributions using Neural Stochastic Differential Equations
    Sumit Jha, Rickard Ewetz, Alvaro Velasquez, Susmit Jha
    30th International Joint Conference on Artificial Intelligence (IJCAI), 2021
    Paper (PDF)

  49. Trinity: Trust, Resilience and Interpretability of Machine Learning Models
    Susmit Jha, Brian Jalaian, Anirban Roy, Gunjan Verma
    Game Theory and Machine Learning for Cyber Security (Book, 2021)
    Paper (PDF)

  50. Detecting OODs as datapoints with High Uncertainty
    Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Oleg Sokolsky, Insup Lee
    Uncertainty & Robustness in Deep Learning Workshop @ ICML 2021
    Paper (PDF)

  51. MISA: Online Defense of Trojaned Models using Misattributions
    Panagiota Kiourti, Wenchao Li, Anirban Roy, Karan Sikka, Susmit Jha
    ACSAC 2021
    Paper (PDF)

  52. Automated Synthesis of Quantum Circuits using Symbolic Abstractions and Decision Procedures
    Alvaro Velasquez, Sumit Kumar Jha, Rickard Ewetz, Susmit Jha
    54th IEEE International Symposium on Circuits and Systems (ISCAS) 2021
    Paper (PDF)

  53. Learning Certified Control Using Contraction Metric
    Dawei Sun, Susmit Jha, Chuchu Fan.
    Conference on Robot Learning (CoRL) 2020
    Paper (PDF)

  54. On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
    Uyeong Jang, Susmit Jha, Somesh Jha
    8th International Conference on Learning Representations (ICLR) 2020
    Paper (PDF)

  55. Estimating the Density of States of Boolean Satisfiability Problems on Classical and Quantum Computing Platforms
    Tuhin Sahai, Anurag Mishra, Jose Miguel Pasini, Susmit Jha.
    34th AAAI Conference on Artificial Intelligence (AAAI) 2020 (Oral)
    Paper (PDF)

  56. Model-Centered Assurance for Autonomous Systems
    Susmit Jha, John Rushby and Natarajan Shankar
    39th International Conference on Computer Safety, Reliability and Security (SafeComp), 2020
    Paper (PDF)

  57. TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
    Panagiota Kiourti, Kacper Wardega, Susmit Jha and Wenchao Li.
    57th ACM/IEEE Design Automation Conference (DAC), July 2020
    Paper (PDF)

  58. Attribution-Based Confidence (ABC) Metric For Deep Neural Networks
    Susmit Jha, Sunny Raj, Steven Fernandes, Sumit Kumar Jha, Somesh Jha, Jalaian Brian, Gunjan Verma and Ananthram Swami.
    Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019
    Paper (PDF)

  59. TRINITY: Trust, Resilience and Interpretability of AI (Tutorial)
    Susmit Jha
    12th Workshop on Numerical Software Verification 2019
    Paper | Slides (PDF)

  60. Logic Extraction for Explainable AI
    Susmit Jha
    Workshop on Formal Methods for ML-Enabled Autonomous Systems Affiliated with CAV 2019
    Paper (PDF) | Slides (PDF)

  61. Attribution-driven Causal Analysis for Detection of Adversarial Examples.
    Susmit Jha, Sunny Raj, Steven Fernandes, Sumit Kumar Jha, Somesh Jha, Jalaian Brian, Gunjan Verma and Ananthram Swami.
    Workshop on Safe Machine Learning: Specification, Robustness and Assurance at International Conference on Learning Representations (SafeML/ICLR), 2019
    Paper (PDF)

  62. Sherlock - A Tool for Verification of Neural Network Feedback Systems: Demo Abstract. (Best Demo Award)
    Souradeep Dutta, Xin Chen, Susmit Jha, Sriram Sankaranarayanan and Ashish Tiwari.
    22nd ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2019
    Paper (PDF)

  63. TeLEx: Learning signal temporal logic from positive examples using tightness metric.
    Susmit Jha, Ashish Tiwari, Sanjit A. Seshia, Tuhin Sahai and Natarajan Shankar.
    Formal Methods in System Design (FMSD), 2019
    Paper (PDF)

  64. A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems.
    Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin
    IEEE American Control Conference (ACC), 2019
    Paper (PDF)

  65. Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions.
    Susmit Jha and John Rushby.
    AAAI Spring Symposium, Towards Conscious AI Systems, 2019
    Paper (PDF)

  66. Sherlock: A Tool for Verification of Deep Neural Networks.
    Souradeep Dutta, Taisa Kushner, Susmit Jha, Sriram Sankaranarayanan,Natarajan Shankar, Ashish Tiwari.
    AAAI Spring Symposium on Verification of Neural Networks (VNN), 2019.
    Paper (PDF)

  67. Learning Task Specifications from Demonstrations.
    Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho and Sanjit A. Seshia.
    32nd International Conference on Neural Information Processing Systems (NeurIPS), 2018
    Paper (PDF)

  68. Safe Autonomy Under Perception Uncertainty Using Chance-Constrained Temporal Logic.
    Susmit Jha, Vasumathi Raman, Dorsa Sadigh, and Sanjit A. Seshia.
    Journal of Automated Reasoning, 60(1):43–62, 2018.
    Paper (PDF)

  69. Data-efficient Learning of Robust Control Policies.
    Susmit Jha and Patrick Lincoln.
    56th IEEE Allerton Control Conference, 2018
    Paper (PDF)

  70. Explaining AI Decisions Using Efficient Methods for Learning Sparse Boolean Formulae.
    Susmit Jha, Tuhin Sahai, Vasumathi Raman, Alessandro Pinto and Michael Francis.
    Journal of Automated Reasoning, 2018
    Paper (PDF)

  71. Detecting Adversarial Examples Using Data Manifolds.
    Susmit Jha, Uyeong Jang, Somesh Jha and Brian Jalaian.
    IEEE Military Communications Conference (MILCOM), 2018 (Also accepted at NATO SET 262 Meeting)
    Paper (PDF)

  72. Duality-Based Nested Controller Synthesis from STL Specifications for Stochastic Linear Systems.
    Susmit Jha, Sunny Raj, Sumit Kumar Jha and Natarajan Shankar.
    16th International Conference on Formal Modeling and Analysis of Timed Systems (FORMATS), 2018.
    Paper (PDF)

  73. Learning and Verification of Feedback Control Systems using Feedforward Neural Networks.
    Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, Ashish Tiwari.
    IFAC Conference on Analysis and Design of Hybrid Systems, 2018
    Paper (PDF)

  74. Model, Data and Reward Repair: Trusted Machine Learning for Markov Decision Processes.
    Shalini Ghosh, Susmit Jha, Ashish Tiwari, Patrick Lincoln, Xiaojin Zhu.
    Workshop on Dependable and Secure Machine Learning at IEEE/IFIP International Conference on Dependable Systems and Networks (DSML/DSN), 2018.
    Paper (PDF)

  75. Output Range Analysis for Deep Feedforward Neural Networks.
    Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, Ashish Tiwari.
    NASA Formal Methods (NFM), 2018
    Paper (PDF)

  76. Trusted Neural Networks for Safety-Constrained Autonomous Control.
    Shalini Ghosh, Amaury Mercier, Dheeraj Pichapati, Susmit Jha, Vinod Yegneswaran, Patrick Lincoln.
    DISE1: Joint Workshop on Machine Learning for Safety-Critical Applications in Engineering at DISE/ICML, 2018
    Paper (PDF)

  77. Will distributed computing revolutionize peace? The emergence of battlefield IoT.
    T. Abdelzaher, N. Ayanian, T. Basar, S. Diggavi, J. Diesner, D. Ganesan, R. Govindan, S. Jha, T. Lepoint, B. Marlin, K. Nahrstedt, D. Nicol, R. Rajkumar, S. Russell, S. Seshia, F. Sha, P. Shenoy, M. Srivastava, G. Sukhatme, A. Swami, P. Tabuada, D. Towsley, N. Vaidya, and V. Veeravalli
    IEEE Int’l Conference on Distributed Computing Systems, 2018.
    Paper (URL)

  78. TeLEx: Passive STL Learning Using Only Positive Examples.
    Susmit Jha, Ashish Tiwari, Sanjit A. Seshia, Natarajan Shankar, and Tuhin Sahai.
    17th International Conference on Runtime Verification (RV), 2017
    Paper (PDF)

  79. On Learning Sparse Boolean Formulae For Explaining AI Decisions.
    Susmit Jha, Vasumathi Raman, Alessandro Pinto, Tuhin Sahai, and Michael Francis.
    NASA Formal Methods (NFM), 2017
    Paper (PDF)

  80. A Theory of Formal Synthesis via Inductive Learning.
    Susmit Jha and Sanjit Seshia.

    Acta Informatica, 2017
    Paper (PDF)