research
∙
06/24/2022
Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
Neural networks have been widely applied in security applications such a...
share
research
∙
06/05/2022
Geometric Theory for Program Testing
Formal methods for verification of programs are extended to testing of p...
research
∙
04/02/2022
Paoding: Supervised Robustness-preserving Data-free Neural Network Pruning
When deploying pre-trained neural network models in real-world applicati...
research
∙
03/21/2022
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
Recent years have seen the wide application of NLP models in crucial are...
research
∙
12/31/2021
DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
Understanding how the predictions of deep learning models are formed dur...
research
∙
12/29/2021
Repairing Adversarial Texts through Perturbation
It is known that neural networks are subject to attacks through adversar...
research
∙
10/06/2021
Generalizing Neural Networks by Reflecting Deviating Data in Production
Trained with a sufficiently large training and testing dataset, Deep Neu...
research
∙
09/25/2021
Constructing Regression Dataset from Code Evolution History
Bug datasets consisting of real-world bugs are important artifacts for r...
research
∙
07/17/2021
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
Although deep learning has demonstrated astonishing performance in many ...
research
∙
03/03/2021
Self-Checking Deep Neural Networks in Deployment
The widespread adoption of Deep Neural Networks (DNNs) in important doma...
research
∙
03/03/2021
Extracting Optimal Explanations for Ensemble Trees via Logical Reasoning
Ensemble trees are a popular machine learning model which often yields h...
research
∙
05/12/2020
N-PAT: A Nested Model-Checker
N-PAT is a new model-checking tool that supports the verification of nes...
research
∙
03/18/2020
Automated synthesis of local time requirement for service composition
Service composition aims at achieving a business goal by composing exist...
research
∙
11/14/2019
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
Deep neural networks (DNN) are increasingly applied in safety-critical s...
research
∙
10/03/2019
Silas: High Performance, Explainable and Verifiable Machine Learning
This paper introduces a new classification tool named Silas, which is bu...
research
∙
10/03/2019
GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems
While AI techniques have found many successful applications in autonomou...
research
∙
09/22/2019
Analyzing Recurrent Neural Network by Probabilistic Abstraction
Neural network is becoming the dominant approach for solving many real-w...
research
∙
06/24/2019