Recent Publications

Askhayaa Magesh, Venu V Veeravalli, Susmit Jha, Anirban Roy (2024). Principled OOD Detection via Multiple Testing. In Journal of Machine Learning Research, 2023.

PDF Cite Project

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

PDF Cite Project

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

PDF Cite Project

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

PDF Cite Project Project

Lyu, Weimin, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, Chao Chen (2023). Task-agnostic detector for insertion-based backdoor attacks. In NAACL Findings, 2024.

PDF Cite Project

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

PDF Cite Project

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

PDF Cite Project Project

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

PDF Cite Project Project

Sumit Jha, Andre Beckus, George Atia, Susmit Jha, Rickard Ewetez (2023). Exploring The Predictive Capabilities of AlphaFold Using Adversarial Protein Sequences. In IEEE Transactions on Artificial Intelligence 2024.

PDF Cite Project

Matthew Walmer, Karan Sikka, Indranil Sur, Abhinav Shrivastava, Susmit Jha (2023). Dual-Key Multimodal Backdoors for Visual Question Answering. In IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023.

PDF Cite Project

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

PDF Cite Project Project

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

PDF Cite Project Project Project

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

PDF Cite Project Project

Adam 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 (2023). AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 (Benchmarks and Datasets).

PDF Cite

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

PDF Cite Project Project

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

Cite Project Project Project Project

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

PDF Cite Project

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

Cite Project Project

Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Yahan Yang, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee (2022). CODiT: Conformal Out-of-Distribution Detection in Time-Series Data for Cyber-Physical Systems. In ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023).

PDF Cite Project Project

Meet P Vadera, Jinyang Li, Adam D Cobb, Brian Jalaian, Tarek Abdelzaher, Benjamin M Marlin (2022). URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference methods. In MLSys 2022.

PDF Cite Code Dataset Project Poster Video Source Document #

Adam D Cobb, Brian Jalaian (2021). Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting. In UAI 2021.

PDF Cite Code Dataset Project Poster Video Source Document Blog Post

Edmond Cunningham, Adam Cobb, Susmit Jha (2021). Principal Manifold Flows. In 39th International Conference on Machine Learning (ICML), 2022.

PDF Cite Project Project Project DOI

Manoj Acharya, Anirban Roy, Kaushik Koneripalli, Susmit Jha, Christopher Kanan, Ajay Divakaran (2021). Detecting out-of-context objects using graph contextual reasoning network.. In 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022.

PDF Cite Project Project Project DOI

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

PDF Cite Project Project Project DOI

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

PDF Cite Project Project DOI

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

PDF Cite Project Project Project

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

PDF Cite Project Project Project DOI

Panagiota Kiourti, Kacper Wargeda, Susmit Jha, Wenchao Li (2020). TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning. In 57th ACM/IEEE Design Automation Conference 2020.

PDF Cite Code Project Project Project Project DOI

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

PDF Cite Code Project Project Project

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

PDF Cite Project Project Project Project

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

PDF Cite Project Project Project Project

Uyeong Jang, Susmit Jha, Somesh Jha (2020). On the Need for Topology-Aware Generative Models for Manifold-Based Defenses. In ICLR 2020.

PDF Cite Project Project Project Project

Susmit Jha, Sunny Raj, Steven Fernandes, Sumit Jha, Somesh Jha, Brian Jalaian, Gunjan Verma, Ananthram Swami (2019). Attribution-Based Confidence Metric For Deep Neural Network. In NeurIPS 2019.

PDF Cite Project Project Project

Susmit Jha, Ashish Tiwari, Sanjit A. Seshia, Tuhin Sahai, Natarajan Shankar (2019). TeLEx: learning signal temporal logic from positive examples using tightness metric. In Formal Methods in System Design, Vol 54, 2019.

PDF Cite Project Project Project

Souradeep Dutta, Taisa Kushner, Susmit Jha, Sriram Sankaranarayanan, Ashish Tiwari (2019). Sherlock : A Tool for Verification of Deep Neural Networks. In AAAI Spring Symposium on NNV 2018.

PDF Cite Code Project Project

Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Oleg Sokolsky, Insup Lee (2019). Detecting OODs as datapoints with high uncertainty. In Uncertainty & Robustness in Deep Learning Workshop @ ICML 2021.

PDF Cite Project Project Project

Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin (2019). A risk-sensitive finite-time reachability approach for safety of stochastic dynamic systems. In ACC 2019.

PDF Cite Code Project DOI

Marcell J. Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit A. Seshia (2018). Learning Task Specifications from Demonstrations. In NeurIPS 2018.

PDF Cite Code Project Project Project

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

PDF Cite Project Project Project

Marcell J. Vazquez-Chanlatte, Uyeong Jang, Somesh Jha, Brian Jalaian (2018). Detecting Adversarial Examples Using Data Manifolds. In IEEE Military Communications Conference (MILCOM) 2018.

PDF Cite Project Project Project DOI

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

PDF Cite Project Project Project

Susmit Jha, Vasumathi Raman, Dorsa Sadigh, Sanjit A. Seshia (2018). Safe autonomy under perception uncertainty using chance-constrained temporal logic. In Journal of Automated Reasoning, 2018.

PDF Cite Project Project Project

Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, Ashish Tiwari (2018). Output range analysis for deep neural networks. In NASA Formal Methods 2018.

PDF Cite Code Project Project Project

Anirban Roy, Sinisa Todorovic (2018). Learning to learn second-order back-propagation for CNNs using LSTMs. In ICPR.

PDF Cite Code Dataset Project Poster Video Source Document Custom Link

Souradeep Dutta, Susmit Jha, Sriram Sankaranarayanan, Ashish Tiwari (2018). Learning and Verification of Feedback Control Systems using Feedforward Neural Networks. In ADHS 2018.

PDF Cite Code Project Project DOI

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

PDF Cite Project Project Project DOI

Karuna Ahuja, Karan Sikka, Anirban Roy, Ajay Divakaran (0001). Understanding visual ads by aligning symbols and objects using co-attention. In CVPR Workshop.

PDF Cite Code Dataset Project Poster Video Source Document Custom Link

Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja, Devi Parikh, Ajay Divakaran (0001). Align2ground: Weakly supervised phrase grounding guided by image-caption alignment. In ICCV.

PDF Cite Code Dataset Project Poster Video Source Document Custom Link