Search Results - "Urban, Caterina"

Preface of the special issue on the conference on Computer-Aided Verification 2020 and 2021 by Albarghouthi, Aws, Leino, Rustan, Silva, Alexandra, Urban, Caterina

Get full text

Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations by Munakata, Satoshi, Urban, Caterina, Yokoyama, Haruki, Yamamoto, Koji, Munakata, Kazuki

“…In this paper, we propose the first verification method for attention robustness, i.e., the local robustness of the changes in the saliency-map against…”
Get full text

Abstract Interpretation as Automated Deduction by D’Silva, Vijay, Urban, Caterina

“…Automata theory, algorithmic deduction and abstract interpretation provide the foundation behind three approaches to implementing program verifiers. This…”
Get full text

Inference of ranking functions for proving temporal properties by abstract interpretation by Urban, Caterina, Miné, Antoine

“…We present new static analysis methods for proving liveness properties of programs. In particular, with reference to the hierarchy of temporal properties…”
Get full text

What Programs Want: Automatic Inference of Input Data Specifications by Urban, Caterina

“…Nowadays, as machine-learned software quickly permeates our society, we are becoming increasingly vulnerable to programming errors in the data pre-processing…”
Get full text

A Review of Formal Methods applied to Machine Learning by Urban, Caterina, Miné, Antoine

“…We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems. Formal methods can provide rigorous…”
Get full text

Abstract Interpretation-Based Data Leakage Static Analysis by Drobnjaković, Filip, Subotić, Pavle, Urban, Caterina

“…Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model…”
Get full text

On Using Certified Training towards Empirical Robustness by De Palma, Alessandro, Durand, Serge, Chihani, Zakaria, Terrier, François, Urban, Caterina

“…Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step…”
Get full text

Abstract Interpretation-Based Feature Importance for SVMs by Pal, Abhinandan, Ranzato, Francesco, Urban, Caterina, Zanella, Marco

“…We propose a symbolic representation for support vector machines (SVMs) by means of abstract interpretation, a well-known and successful technique for…”
Get full text

Fair Training of Decision Tree Classifiers by Ranzato, Francesco, Urban, Caterina, Zanella, Marco

“…We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and…”
Get full text

Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations by Munakata, Satoshi, Urban, Caterina, Yokoyama, Haruki, Yamamoto, Koji, Munakata, Kazuki

“…It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of…”
Get full text

Perfectly Parallel Fairness Certification of Neural Networks by Urban, Caterina, Christakis, Maria, Wüstholz, Valentin, Zhang, Fuyuan

“…Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case…”
Get full text

Permission Inference for Array Programs by Dohrau, Jérôme, Summers, Alexander J, Urban, Caterina, Münger, Severin, Müller, Peter

“…Information about the memory locations accessed by a program is, for instance, required for program parallelisation and program verification. Existing…”
Get full text