English
Related papers

Related papers: A Formally Verified Robustness Certifier for Neura…

200 papers

The topic of provable deep neural network robustness has raised considerable interest in recent years. Most research has focused on adversarial robustness, which studies the robustness of perceptive models in the neighbourhood of particular…

Machine Learning · Computer Science 2019-11-26 Julien Girard-Satabin , Guillaume Charpiat , Zakaria Chihani , Marc Schoenauer

Robustness in deep neural networks and machine learning algorithms in general is an open research challenge. In particular, it is difficult to ensure algorithmic performance is maintained on out-of-distribution inputs or anomalous instances…

Machine Learning · Computer Science 2022-11-23 Natalie Abreu , Nathan Vaska , Victoria Helus

Neural networks offer a computationally efficient approximation of model predictive control, but they lack guarantees on the resulting controlled system's properties. Formal certification of neural networks is crucial for ensuring safety,…

Optimization and Control · Mathematics 2025-02-05 Philip Sosnin , Calvin Tsay

Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input). However, many use cases of neural network…

Machine Learning · Computer Science 2024-03-19 Suhas Kotha , Christopher Brix , Zico Kolter , Krishnamurthy Dvijotham , Huan Zhang

Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…

Machine Learning · Computer Science 2022-10-27 Pratik Vaishnavi , Kevin Eykholt , Amir Rahmati

In this paper, we consider the problem of certifying the robustness of neural networks to perturbed and adversarial input data. Such certification is imperative for the application of neural networks in safety-critical decision-making and…

Machine Learning · Computer Science 2020-09-21 Brendon G. Anderson , Ziye Ma , Jingqi Li , Somayeh Sojoudi

Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high…

Machine Learning · Computer Science 2017-11-07 Matthias Hein , Maksym Andriushchenko

We consider the problem of whether a Neural Network (NN) model satisfies global individual fairness. Individual Fairness suggests that similar individuals with respect to a certain task are to be treated similarly by the decision model. In…

Machine Learning · Computer Science 2022-05-23 Haitham Khedr , Yasser Shoukry

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either safe or unsafe (robust or not robust). This binary encoding…

Artificial Intelligence · Computer Science 2025-05-09 Luca Marzari , Isabella Mastroeni , Alessandro Farinelli

As deep learning models continue to advance and are increasingly utilized in real-world systems, the issue of robustness remains a major challenge. Existing certified training methods produce models that achieve high provable robustness…

Machine Learning · Computer Science 2023-07-26 Zhakshylyk Nurlanov , Frank R. Schmidt , Florian Bernard

Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustness certificates is important to guarantee that test…

Machine Learning · Computer Science 2025-03-04 Mahalakshmi Sabanayagam , Lukas Gosch , Stephan Günnemann , Debarghya Ghoshdastidar

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address…

Machine Learning · Computer Science 2020-12-09 Pengfei Chen , Junjie Ye , Guangyong Chen , Jingwei Zhao , Pheng-Ann Heng

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits - minimal subnetworks responsible for specific…

Artificial Intelligence · Computer Science 2026-03-03 Alaa Anani , Tobias Lorenz , Bernt Schiele , Mario Fritz , Jonas Fischer

Output reachability and adversarial robustness are among the most relevant safety properties of neural networks. We show that in the context of Message Passing Neural Networks (MPNN), a common Graph Neural Network (GNN) model, formal…

Machine Learning · Computer Science 2022-10-05 Marco Sälzer , Martin Lange

Testing remains the primary method to evaluate the accuracy of neural network perception systems. Prior work on the formal verification of neural network perception models has been limited to notions of local adversarial robustness for…

Machine Learning · Computer Science 2020-12-18 Chris R. Serrano , Pape M. Sylla , Michael A. Warren

Neural network verification tools currently support only a narrow class of specifications, typically expressed as low-level constraints over raw inputs and outputs. This limitation significantly hinders their adoption and practical…

Machine Learning · Computer Science 2026-03-04 Yizhak Y. Elboher , Reuven Peleg , Zhouxing Shi , Guy Katz , Jan Křetínský

Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Thomas Massena , Corentin Friedrich , Franck Mamalet , Mathieu Serrurier

Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e.g. translations, rotations, etc. Current input deformation certification…

Machine Learning · Computer Science 2021-12-21 Motasem Alfarra , Adel Bibi , Naeemullah Khan , Philip H. S. Torr , Bernard Ghanem

Deep Neural Networks are increasingly adopted in critical tasks that require a high level of safety, e.g., autonomous driving. While state-of-the-art verifiers can be employed to check whether a DNN is unsafe w.r.t. some given property…

Artificial Intelligence · Computer Science 2023-06-21 Luca Marzari , Davide Corsi , Ferdinando Cicalese , Alessandro Farinelli

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That…

Machine Learning · Computer Science 2023-03-20 Chuqin Geng , Nham Le , Xiaojie Xu , Zhaoyue Wang , Arie Gurfinkel , Xujie Si