Sotabase

Career

· Full Professor of Computer Science, ETH Zurich2022–
· Founder and Scientific Director, INSAIT - Institute for Computer Science, Artificial Intelligence and Technology2022–
· Associate Professor, ETH Zurich2017–2022
· Assistant Professor, ETH Zurich2012–2017
· Research Staff Member, IBM T.J. Watson Research Center2007–2011
· PhD in Computer Science, University of Cambridge2003–2008
· Bachelor's degree, Simon Fraser University1996–2001

Publications (290)

Securify: Practical Security Analysis of Smart Contracts
Conference on Computer and Communications Security · 2018
1,055
cited
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
IEEE Symposium on Security and Privacy · 2018
966
cited
An abstract domain for certifying neural networks
Proc. ACM Program. Lang. · 2019
778
cited
Code completion with statistical language models
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2014
705
cited
Differentiable Abstract Interpretation for Provably Robust Neural Networks
International Conference on Machine Learning · 2018
567
cited
Fast and Effective Robustness Certification
Neural Information Processing Systems · 2018
519
cited
Predicting Program Properties from "Big Code"
ACM-SIGACT Symposium on Principles of Programming Languages · 2015
400
cited
Learning to Fuzz from Symbolic Execution with Application to Smart Contracts
Conference on Computer and Communications Security · 2019
273
cited
Probabilistic model for code with decision trees
Conference on Object-Oriented Programming Systems, Languages, and Applications · 2016
270
cited
VerX: Safety Verification of Smart Contracts
IEEE Symposium on Security and Privacy · 2020
240
cited
Large Language Models for Code: Security Hardening and Adversarial Testing
Conference on Computer and Communications Security · 2023
209
cited
PHOG: Probabilistic Model for Code
International Conference on Machine Learning · 2016
202
cited
PSI: Exact Symbolic Inference for Probabilistic Programs
International Conference on Computer Aided Verification · 2016
190
cited
Beyond the Single Neuron Convex Barrier for Neural Network Certification
Neural Information Processing Systems · 2019
188
cited
Adversarial Training and Provable Defenses: Bridging the Gap
International Conference on Learning Representations · 2020
184
cited
Boosting Robustness Certification of Neural Networks
International Conference on Learning Representations · 2018
181
cited
DL2: Training and Querying Neural Networks with Logic
International Conference on Machine Learning · 2019
181
cited
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
International Conference on Learning Representations · 2023
169
cited
Silq: a high-level quantum language with safe uncomputation and intuitive semantics
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2020
167
cited
Learning programs from noisy data
ACM-SIGACT Symposium on Principles of Programming Languages · 2016
164
cited
Sotabase
Martin Vechev | Researcher Profile | Sotabase | Sotabase