Sotabase

Career

· Assistant Professor, University of Chicago2024–
· Doctor of Philosophy (Ph.D.), Columbia University in the City of New York2016–2023
· Master's degree, Purdue University2014–
· Bachelor's degree, Hong Kong Baptist University

Publications (33)

DeepXplore: Automated Whitebox Testing of Deep Learning Systems
Symposium on Operating Systems Principles · 2017
1,481
cited
DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars
International Conference on Software Engineering · 2017
1,443
cited
Formal Security Analysis of Neural Networks using Symbolic Intervals
USENIX Security Symposium · 2018
512
cited
Efficient Formal Safety Analysis of Neural Networks
Neural Information Processing Systems · 2018
433
cited
NEUZZ: Efficient Fuzzing with Neural Program Smoothing
IEEE Symposium on Security and Privacy · 2018
211
cited
HERCULE: attack story reconstruction via community discovery on correlated log graph
Asia-Pacific Computer Systems Architecture Conference · 2016
175
cited
Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity
arXiv.org · 2020
114
cited
Can Large Language Models Reason about Program Invariants?
International Conference on Machine Learning · 2023
108
cited
Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems
arXiv.org · 2017
108
cited
Python probabilistic type inference with natural language support
SIGSOFT FSE · 2016
104
cited
DeepXplore
Communications of the ACM · 2019
94
cited
SymLM: Predicting Function Names in Stripped Binaries via Context-Sensitive Execution-Aware Code Embeddings
Conference on Computer and Communications Security · 2022
94
cited
HVLearn: Automated Black-Box Analysis of Hostname Verification in SSL/TLS Implementations
IEEE Symposium on Security and Privacy · 2017
88
cited
XDA: Accurate, Robust Disassembly with Transfer Learning
Network and Distributed System Security Symposium · 2020
75
cited
StateFormer: fine-grained type recovery from binaries using generative state modeling
ESEC/SIGSOFT FSE · 2021
72
cited
TRACED: Execution-Aware Pre-Training for Source Code
International Conference on Software Engineering · 2023
55
cited
LEAPS: Detecting Camouflaged Attacks with Statistical Learning Guided by Program Analysis
2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks · 2015
46
cited
NEUZZ: Efficient Fuzzing with Neural Program Learning
arXiv.org · 2018
42
cited
Learning Approximate Execution Semantics From Traces for Binary Function Similarity
IEEE Transactions on Software Engineering · 2023
41
cited
SmartInv: Multimodal Learning for Smart Contract Invariant Inference
IEEE Symposium on Security and Privacy · 2024
31
cited
Sotabase
Kexin Pei | Researcher Profile | Sotabase | Sotabase