6 citations · 14 across the 8 of their papers we have counts for
9 papers
A proof-theoretic approach to abstract interpretation
Vijay D'Silva, Alessandra Palmigiano, Apostolos Tzimoulis +1
This paper develops a proof-theoretic framework for abstract interpretation by systematically associating logical systems with finite abstractions. Building on earlier work on the…
Abstract Interpretation-Based Data Leakage Static Analysis
Filip Drobnjaković, Pavle Subotić, Caterina Urban
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. This phenomenon renders…
Abstract Interpretation-Based Feature Importance for SVMs
Abhinandan Pal, Francesco Ranzato, Caterina Urban +1
We propose a symbolic representation for support vector machines (SVMs) by means of abstract interpretation, a well-known and successful technique for designing and implementing st…
Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations
Satoshi Munakata, Caterina Urban, Haruki Yokoyama +2
It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of atten…
A Review of Formal Methods applied to Machine Learning
Caterina Urban, Antoine Miné
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 correctness guarantees…
Fair Training of Decision Tree Classifiers
Francesco Ranzato, Caterina Urban, Marco Zanella
We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and individual fairness. In…
What Programs Want: Automatic Inference of Input Data Specifications
Caterina Urban
Nowadays, as machine-learned software quickly permeates our society, we are becoming increasingly vulnerable to programming errors in the data pre-processing or training software,…
Perfectly Parallel Fairness Certification of Neural Networks
Caterina Urban, Maria Christakis, Valentin Wüstholz +1
Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the tr…
Permission Inference for Array Programs
Jérôme Dohrau, Alexander J. Summers, Caterina Urban +2
Information about the memory locations accessed by a program is, for instance, required for program parallelisation and program verification. Existing inference techniques for this…