|
I am an assistant professor in the Department of Computer Science at Colorado State University.
I was a post-doctoral researcher in CMU Cylab
hosted by Dr. Corina Pasareanu and
graduated with a PhD from the School of Computer Science
at Georgia Tech. [CSB 372] [ravi.mangal@colostate.edu] [CV] [Google Scholar] |
 |
Research Interests
I am interested in analyzing the safety and security of software systems using formal methods. I focus on evaluating and improving the trustworthiness, i.e., safety, security, and interpretability, of AI-enabled systems such as coding assistants and robots.Prospective Students
I am always open to interacting with and supervising students who are interested in or curious about topics related to my research. Feel free to send me an email outlining your interests or drop by my office!Teaching
CS 580B1/CS480B1: Trustworthy AI (Fall 2026)CS 445: Introduction to Machine Learning (Spring 2026)
CS 454: Principles of Programming Languages (Spring 2025)
CS 580B1: Trustworthy Machine Learning (Fall 2024)
Students
Ronaldo Canizales (PhD)William Scarbro (PhD; Co-advised with Sanjay Rajopadhye)
Hasan Najib Mahmud (PhD)
Rahul Zalkikar (PhD)
Nathaniel Enis (BS)
Graduated Students
Harshit Singh (MS) — Evaluation of Robustness of LLMs for Function Name PredictionMd Abdul Hannan (MS) — The Impact of Few-Shot Examples for LLM-based Code Vulnerability Detection [Next: PhD at UT Dallas]
Ben Blount (BS) — A Mechanization of Named and Locally Nameless Untyped Lambda Calculus in Rocq
Papers
(* indicates equal contribution, (#) indicates alphabetical ordering)
2026
- Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Ronaldo Canizales, Divya Gopinath, Corina Pasareanu, Ravi Mangal
Preprint, 2026
- SecCodePRM: A Process Reward Model for Code Security
Weichen Yu, Ravi Mangal, Yinyi Luo, Kai Hu, Jingxuan He, Corina Pasareanu, Matt Fredrikson
43rd International Conference on Machine Learning (ICML), 2026
- When “Correct” Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Yibo Peng*, James Song*, Lei Li*, Xinyu Yang, Mihai Christodorescu, Ravi Mangal, Corina Pasareanu, Haizhong Zheng, Beidi Chen
64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026
- Interval POMDP Shielding for Imperfect-Perception Agents
William Scarbro, Ravi Mangal
Preprint, 2026
- On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection
Md Abdul Hannan*, Ronghao Ni*, Chi Zhang, Limin Jia, Ravi Mangal, Corina Pasareanu
LLM Assisted Security and Trust Exploration (LAST-X) Workshop, 2026 (Co-located with NDSS 2026)
2025
- A Mixture of Linear Corrections Generates Secure Code
Weichen Yu, Ravi Mangal, Terry Yue Zhuo, Matt Fredrikson, Corina Pasareanu
Preprint, 2025
- Conformal Safety Shielding for Imperfect-Perception Agents
William Scarbro*, Calum Imrie*, Sinem Getir Yaman, Kavan Fatehi, Corina Pasareanu, Radu Calinescu, Ravi Mangal
International Conference on Runtime Verification (RV), 2025
- Scenario-based Compositional Verification of Autonomous Systems with Neural Perception
Christopher Watson, Rajeev Alur, Divya Gopinath, Ravi Mangal, Corina Pasareanu
8th International Symposium on AI Verification (SAIV), 2025 (Co-located with CAV 2025)
- Validating Mechanistic Interpretations: An Axiomatic Approach
Nils Palumbo, Ravi Mangal, Zifan Wang, Saranya Vijayakumar, Corina Pasareanu, Somesh Jha
42nd International Conference on Machine Learning (ICML), 2025
- Monitoring Safety Properties for Autonomous Driving Systems with Vision-Language Models
Felipe Toledo, Sebastian Elbaum, Divya Gopinath, Ramneet Kaur, Ravi Mangal, Corina Pasareanu, Anirban Roy, Susmit Jha
Engineering Reliable Autonomous Systems (ERAS), 2025
- Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)
Boyue Caroline Hu, Divya Gopinath, Ravi Mangal, Nina Narodytska, Susmit Jha, Corina Pasareanu
4th International Conference on AI Engineering – Software Engineering for AI (CAIN), 2025 (Co-located with ICSE 2025)
Distinguished Paper Award Candidate
2024
- Formal Verification Techniques for Vision-based Autonomous Systems – A Survey
Sayan Mitra, Corina Pasareanu, Pavithra Prabhakar, Sanjit A. Seshia, Ravi Mangal, Yangge Li, Christopher Watson, Divya Gopinath, Huafeng Yu
Principles of Verification: Cycling the Probabilistic Landscape: Essays Dedicated to Joost-Pieter Katoen on the Occasion of His 60th Birthday, Part III, 2024
- Attacks and Defenses for Large Language Models on Coding Tasks
Chi Zhang, Zifan Wang, Ruoshi Zhao, Ravi Mangal, Matt Fredrikson, Limin Jia, Corina Pasareanu
NIER track of the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE-NIER), 2024
- Concept-based Analysis of Neural Networks via Vision-Language Models
Ravi Mangal, Nina Narodytska, Divya Gopinath, Boyue Caroline Hu, Anirban Roy, Susmit Jha, Corina Pasareanu
7th International Symposium on AI Verification (SAIV), 2024 (Co-located with CAV 2024)
- Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components
(#) Radu Calinescu, Calum Imrie, Ravi Mangal, Genaina Nunes Rodrigues, Corina Pasareanu, Misael Alpizar Santana, and Gricel Vazquez
IEEE Transactions on Software Engineering (TSE), 2024
2023
- Is Certifying Lp Robustness Still Worthwhile?
Ravi Mangal*, Klas Leino*, Zifan Wang*, Kai Hu*, Weichen Yu, Corina Pasareanu, Matt Fredrikson, Anupam Datta
Preprint, 2023
- Assumption Generation for Learning-Enabled Autonomous Systems
Corina Pasareanu, Ravi Mangal, Divya Gopinath, and Huafeng Yu
International Conference on Runtime Verification (RV), 2023
- Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study
Corina Pasareanu, Ravi Mangal, Divya Gopinath, Sinem Getir Yaman, Calum Imrie, Radu Calinescu, and Huafeng Yu
International Conference on Computer Aided Verification (CAV), 2023
- On the Perils of Cascading Robust Classifiers
Ravi Mangal*, Zifan Wang*, Chi Zhang*, Klas Leino, Corina Pasareanu, and Matt Fredrikson
International Conference on Learning Representations (ICLR), 2023
[code]
- Feature-Guided Analysis of Neural Networks
(#) Divya Gopinath, Luca Lungeanu, Ravi Mangal, Corina Pasareanu, Siqi Xie, and Huafeng Yu
Fundamental Approaches to Software Engineering (FASE), 2023
2022
- Degradation Attacks on Certifiably Robust Neural Networks
Klas Leino*, Chi Zhang*, Ravi Mangal*, Matt Fredrikson, Bryan Parno, and Corina Pasareanu
Transactions on Machine Learning Research (TMLR), 2022
[code]
- Self-Correcting Neural Networks For Safe Classification
Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson, Bryan Parno, and Corina Pasareanu
Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS), 2022 (Co-located with CAV 2022)
[code]
- A Cascade of Checkers for Run-time Certification of Local Robustness
Ravi Mangal and Corina Pasareanu
Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS), 2022 (Co-located with CAV 2022)
[code]
2020
- Reasoning About Programs in Statistically Modeled First-Order Environments
Ravi Mangal
Dissertation, 2020
- Observational Abstract Interpreters
Ravi Mangal
Preprint, 2020
- Probabilistic Lipschitz Analysis of Neural Networks
Ravi Mangal, Kartik Sarangmath, Aditya V. Nori, and Alex Orso
Static Analysis Symposium (SAS), 2020
[code]
2019
- Robustness of Neural Networks: A Probabilistic and Practical Perspective
Ravi Mangal, Aditya V. Nori, and Alex Orso
NIER track of the 41st IEEE and ACM SIGSOFT International Conference on Software Engineering (ICSE-NIER), 2019
[slides]
- Checking Probabilistic Properties of Neural Networks via Symbolic Methods and Sampling
Ravi Mangal, Aditya V. Nori, and Alessandro Orso
First ICSE Workshop on Testing for Deep Learning and Deep Learning for Testing (DeepTest), 2019 (Co-located with ICSE 2019)
[slides]
- On Optimally Combining Static and Dynamic Analyses For Intensional Program Properties
Ravi Mangal, David Devecsery, and Alessandro Orso
The Southeast Regional Programming Languages Seminar (SERPL), 2019
[slides]
2016
- Accelerating Program Analyses by Cross-Program Training
Sulekha Kulkarni, Ravi Mangal, Xin Zhang, and Mayur Naik
ACM Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA), 2016
[slides]
- Scaling Relational Inference using Proofs and Refutations
Ravi Mangal, Xin Zhang, Aditya Kamath, Aditya V. Nori, and Mayur Naik
AAAI Conference on Artificial Intelligence (AAAI), 2016
[poster]
- Query-guided Maximum Satisfiability
Xin Zhang, Ravi Mangal, Aditya V. Nori, and Mayur Naik
Principles of Programming Languages (POPL), 2016
[slides]
2015
- Volt: A Lazy Grounding Framework for Solving Very Large MaxSAT Instances
Ravi Mangal, Xin Zhang, Aditya V. Nori, and Mayur Naik
International Conference on Theory and Applications of Satisfiability Testing (SAT), 2015
[slides]
- A User-Guided Approach to Program Analysis
Ravi Mangal, Xin Zhang, Aditya V. Nori, and Mayur Naik
ACM Symposium on Foundations of Software Engineering (FSE), 2015
ACM SIGSOFT Distinguished Paper Award
[slides]
- Solving Weighted Constraints with Applications to Program Analysis
Ravi Mangal, Xin Zhang, Mayur Naik, and Aditya V. Nori
SCS Technical Report, GT-CS-15-03, Georgia Institute of Technology, February, 2015
2014
- On Abstraction Refinement for Program Analyses in Datalog
Xin Zhang, Ravi Mangal, Radu Grigore, Mayur Naik, and Hongseok Yang
ACM Conference on Programming Language Design and Implementation (PLDI), 2014
Distinguished Paper Award
[long version] [slides]
- Hybrid Top-Down and Bottom-Up Interprocedural Analysis
Xin Zhang, Ravi Mangal, Mayur Naik, and Hongseok Yang
ACM Conference on Programming Language Design and Implementation (PLDI), 2014
[long version] [slides]
- A Correspondence between Two Approaches to Interprocedural Analysis in the Presence of Join
Ravi Mangal, Mayur Naik, and Hongseok Yang
European Symposium on Programming (ESOP), 2014
Best Paper Award Nominee
[long version] [slides]