CORINA PASAREANU


Principal Scientist (CMU CyLab), Technical Professional Leader -- Data Science (NASA Ames/KBR). [CyLab page] [pcorina@andrew.cmu.edu] [corina.s.pasareanu@nasa.gov]

Bio:
Corina Pasareanu is an ACM Fellow and an IEEE ASE Fellow, working at NASA Ames. She is affiliated with KBR and Carnegie Mellon University's CyLab. Her research interests include model checking, symbolic execution, compositional verification, probabilistic software analysis, autonomy, and security. She is the recipient of several awards, including ETAPS Test of Time Award (2021), ASE Most Influential Paper Award (2018), ESEC/FSE Test of Time Award (2018), ISSTA Retrospective Impact Paper Award (2018), ACM Impact Paper Award (2010), and ICSE 2010 Most Influential Paper Award (2010). She has been serving as Program/General Chair for several conferences including: FASE 2026, ICSE 2025, SEFM 2021, FM 2021, ICST 2020, ISSTA 2020, ESEC/FSE 2018, CAV 2015, ISSTA 2014, ASE 2011, and NFM 2009. She is on the steering committees for the ICSE, ETAPS, TACAS and ISSTA conferences. She is currently an associate editor for IEEE TSE and for STTT, Springer Nature.

Projects:
Adversarial Perturbations and Self-Defenses for Large Language Models on Coding Tasks (PI, selected), Proving the Absence of Timing Side Channels in Cryptographic Applications (AWS, PI), LLM Self-Defense Against Adversarial Attacks for Coding Tasks (CyLab, PI), Trinity:Neurosymbolic Learning and Reasoning (DARPA, CMU PI), Enabling One-Line Rust Verification with Program Synthesis (AWS, Co-PI), Machine Learning for JavaScript Vulnerability Detection (C3.ai DTI, PI), Verifiable Personalization for Federated Learning (CyLab, PI), HUGS: Human-Guided Software Testing and Analysis for Scalable Bug Detection and Repair (NSF, PI), Safety of shared control in autonomous driving (Safe-SCAD) (Assuring Autonomy International Programme, Co-PI), Provably Robust Deep Learning (DARPA GARD, co-PI), Mera: Memoized Ranged Systematic Software Analyses (NSF, Co-PI), ISSTAC: Integrated Symbolic Execution for Space-Time Analysis of Code (DARPA, Co-PI), Symbolic PathFinder: Symbolic Execution for Java Bytecode (NASA, Main developer).
Announcements:
I am a co-organizer of a Shonan seminar on Trusted Automatic Programming with LLMs (Japan, January 2025).
I am Program Co-Chair of ICSE 2025 (Ottawa, Canada, April 2025).
I will give lectures at the L'Aquila Summer School on AI (Italy, May 2025).
I gave a keynote at ASE'24, on Concept-based analysis of neural networks via VLMs (Sacramento, October 2024).
I participated in a Simons Institute meeting on Synthesis (Berkeley, July 2024).
I served on the CAV Award Committee. Please send your nominations!
I gave lectures at the Marktoberdorf Summer School 2023.
I am a Faculty Host for the Carnegie Bosch Fellowship Program. Please apply.

PhD Students and PostDocs:
Book:
Some Recent Papers: See also [Google Scholar] [DBLP].
  • Random Perturbation Attacks on LLMs for Code Generation, Qiulu Peng, Chi Zhang, Ravi Mangal, Corina Pasareanu, Limin Jia , CAIN 2025 (to appear).
  • Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study), Boyue Caroline Hu, Divya Gopinath, Ravi Mangal, Nina Narodytska, Corina Pasareanu, Susmit Jha, CAIN 2025 (to appear).
  • 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, Springer Nature Switzerland, 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, Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (NIER), 2024
  • Evaluating the Trustworthiness of Deep Neural Networks in Deployment--A Comparative Study (Replicability Study), Eduard Pinconschi, Divya Gopinath, Corina Pasareanu, Rui Abreu, 33rd International Symposium on Software Testing and Analysis (ISSTA), 2024.
  • Mechanistically Interpreting a Transformer-based 2-SAT Solver: An Axiomatic Approach, Nils Palumbo, Ravi Mangal, Zifan Wang, Saranya Vijayakumar, Corina S Pasareanu, Somesh Jha, arXiv preprint arXiv:2407.13594, 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 S Pasareanu, International Symposium on AI Verification, 2024.
  • ProInspector: Uncovering Logical Bugs in Protocol Implementations, Zichao Zhang, Limin Jia, Corina Pasareanu, 2024 IEEE 9th European Symposium on Security and Privacy (EuroS&P).
  • Crabtree: Rust API Test Synthesis Guided by Coverage and Type, Yoshiki Takashima, Chanhee Cho, Ruben Martins, Limin Jia, Corina S. Pasareanu, Proc. ACM Program. Lang. 8(OOPSLA2): 618-647 (2024).
  • Does Going Beyond Branch Coverage Make Program Repair Tools More Reliable?, Amirfarhad Nilizadeh, Gary T Leavens, Corina S Pasareanu, Xuan-Bach D Le, David R Cok, 2024 IEEE Conference on Software Testing, Verification and Validation (ICST).
  • Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study, Corina S. Pasareanu, Ravi Mangal, Divya Gopinath, Sinem Getir Yaman, Calum Imrie, Radu Calinescu, Huafeng Yu, in CAV 2023, preprint.
  • Feature-Guided Analysis of Neural Networks, Divya Gopinath, Luca Lungeanu, Ravi Mangal, Corina S. Pasareanu, Siqi Xie, Huanfeng Yu, in FASE 2023.
  • On the Perils of Cascading Robust Classifiers, Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina Pasareanu, Matt Fredrikson, in ICLR 2023.
  • Toward Certified Robustness Against Real-World Distribution Shifts, Haoze Wu, Teruhiro Tagomori, Alexander Robey, Fengjun Yang, Nikolai Matni, Hamed Hassani, George J. Pappas, Corina Pasareanu, Clark Barrett, in SatML 2023.
  • Degradation Attacks on Certifiably Robust Neural Networks, Klas Leino, Chi Zhang, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina Pasareanu, in TMLR 2022.
  • Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components, Radu Calinescu, Calum Imrie, Ravi Mangal, Corina S. Pasareanu, Misael Alpizar Santana, Gricel Vzquez, preprint 2022. (published in TSE Journal 2024)
    • .