English
Related papers

Related papers: Stress-Testing Neural Network Verifiers with Prova…

200 papers

Prior work on neural network verification has focused on specifications that are linear functions of the output of the network, e.g., invariance of the classifier output under adversarial perturbations of the input. In this paper, we extend…

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

The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. In this context, verification involves proving or disproving that an NN…

Machine Learning · Computer Science 2025-08-27 Rudy Bunel , Jingyue Lu , Ilker Turkaslan , Philip H. S. Torr , Pushmeet Kohli , M. Pawan Kumar

Formal verification of neural networks is essential for their deployment in safety-critical areas. Many available formal verification methods have been shown to be instances of a unified Branch and Bound (BaB) formulation. We propose a…

Machine Learning · Computer Science 2019-12-04 Jingyue Lu , M. Pawan Kumar

Robustness verification of neural networks, referring to formally proving that neural networks satisfy robustness properties, is of crucial importance in safety-critical applications, where model failures can result in loss of human life or…

Machine Learning · Computer Science 2026-04-06 Minh Le , Phuong Cao

Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models such as DeepSeek-R1. In complex domains like mathematical…

Machine Learning · Computer Science 2025-10-08 Yuzhen Huang , Weihao Zeng , Xingshan Zeng , Qi Zhu , Junxian He

Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their…

Machine Learning · Computer Science 2019-07-18 He Zhu , Zikang Xiong , Stephen Magill , Suresh Jagannathan

Graph neural networks are becoming increasingly popular in the field of machine learning due to their unique ability to process data structured in graphs. They have also been applied in safety-critical environments where perturbations…

Machine Learning · Computer Science 2025-04-17 Tobias Ladner , Michael Eichelbeck , Matthias Althoff

With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive…

Computation and Language · Computer Science 2022-07-14 Marco Casadio , Ekaterina Komendantskaya , Verena Rieser , Matthew L. Daggitt , Daniel Kienitz , Luca Arnaboldi , Wen Kokke

This paper presents for the first time, to our knowledge, a framework for verifying neural network behavior in power system applications. Up to this moment, neural networks have been applied in power systems as a black-box; this has…

Systems and Control · Electrical Eng. & Systems 2020-07-31 Andreas Venzke , Spyros Chatzivasileiadis

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security,…

Machine Learning · Computer Science 2021-10-06 Aws Albarghouthi

Machine learned models often must abide by certain requirements (e.g., fairness or legal). This has spurred interested in developing approaches that can provably verify whether a model satisfies certain properties. This paper introduces a…

Machine Learning · Computer Science 2020-12-01 Laurens Devos , Wannes Meert , Jesse Davis

Many available formal verification methods have been shown to be instances of a unified Branch-and-Bound (BaB) formulation. We propose a novel machine learning framework that can be used for designing an effective branching strategy as well…

Machine Learning · Computer Science 2021-07-28 Florian Jaeckle , Jingyue Lu , M. Pawan Kumar

Neural networks have become state-of-the-art for computer vision problems because of their ability to efficiently model complex functions from large amounts of data. While neural networks can be shown to perform well empirically for a…

Robotics · Computer Science 2020-03-06 Kyle D. Julian , Ritchie Lee , Mykel J. Kochenderfer

We study the problem of formally verifying the robustness to adversarial examples of support vector machines (SVMs), a major machine learning model for classification and regression tasks. Following a recent stream of works on formal…

Machine Learning · Computer Science 2019-04-29 Francesco Ranzato , Marco Zanella

Learning-based methods could provide solutions to many of the long-standing challenges in control. However, the neural networks (NNs) commonly used in modern learning approaches present substantial challenges for analyzing the resulting…

Machine Learning · Computer Science 2022-02-03 Michael Everett

Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while proper support from the programming language perspective has…

We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate the probability of the event that the property is violated…

Machine Learning · Statistics 2019-02-25 Stefan Webb , Tom Rainforth , Yee Whye Teh , M. Pawan Kumar

Large language models for code generation increasingly rely on synthetic data, where both problem solutions and verification tests are generated by models. While this enables scalable data creation, it introduces a previously unexplored…

Software Engineering · Computer Science 2025-09-26 Srishti Gureja , Elena Tommasone , Jingyi He , Sara Hooker , Matthias Gallé , Marzieh Fadaee