Corina Pasareanu

Corina Pasareanu is a Principal Scientist at Carnegie Mellon University's CyLab and Technical Professional Leader for Data Science at NASA Ames Research Center (working through KBR). She maintains strong affiliations with both CMU's School of Computer Science and NASA Ames, leading cutting-edge research at the intersection of formal verification, AI safety, and software security.

She earned her Ph.D. in Computer Science from Kansas State University in 2001, following MS (1995) and BS (1994) degrees in Computer Science from University Politehcnica of Bucharest. Her academic foundation has propelled her to become a leading expert in verification techniques for complex software systems.

Dr. Pasareanu's research program focuses on model checking, symbolic execution, compositional verification, and probabilistic software analysis, with growing emphasis on ensuring safety and reliability of AI systems. Her work bridges theoretical formal methods with practical applications in autonomous systems and security-critical domains. Recent efforts target verification challenges in large language models and vision-based autonomous systems, developing techniques to provide mathematical guarantees of system behavior despite AI component uncertainties.

Analysis of her publication trends reveals a strategic evolution from foundational verification techniques toward increasingly complex AI systems, with strong emphasis on practical applications in safety-critical contexts. Her work consistently connects theoretical advances in formal methods with real-world security and safety challenges.

Her scientific contributions have earned exceptional recognition:

• ACM Fellow and IEEE ASE Fellow
• 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)
• Multiple historical impact awards including ACM Impact Paper Award (2010) and ICSE Most Influential Paper Award (2010)

Dr. Pasareanu actively mentors the next generation of computer scientists, currently advising PhD students Aymeric Fromherz (with Bryan Parno), Yoshiki Takashima, Zichao Zhang, and Chi Zhang (all with Limin Jia), plus postdoc Ravi Mangal. She has secured substantial research funding from NSF, DARPA, AWS, NASA, and industry partners for projects including 'LLM Self-Defense Against Adversarial Attacks,' 'Trinity: Neurosymbolic Learning and Reasoning,' and 'HUGS: Human-Guided Software Testing.' Her leadership extends to Program Co-Chair for ICSE 2025 and multiple other major conferences, plus service on steering committees for ICSE, ETAPS, TACAS, and ISSTA.

As Principal Scientist at CMU CyLab, she leads research teams developing verification techniques for AI systems, with particular focus on autonomous vehicles and large language models. Her NASA Ames work applies formal methods to space-related autonomous systems, while her collaborations with industry partners translate theoretical advances into practical tools. She remains at the forefront of addressing verification challenges for increasingly complex AI technologies, with upcoming keynotes at CAV 2025 and FormaliSE 2025 demonstrating her continued leadership in the field.