English
Related papers

Related papers: Improving Neural Network Verification through Spur…

200 papers

The growing use of deep neural networks in safety-critical applications makes it necessary to carry out adequate testing to detect and correct any incorrect behavior for corner case inputs before they can be actually used. Deep neural…

Software Engineering · Computer Science 2019-02-19 Jasmine Sekhon , Cody Fleming

From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models. However, the impressive generalization performance of neural networks…

Machine Learning · Computer Science 2021-02-09 Taejong Joo , Uijung Chung

Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Yizhak Y. Elboher , Avraham Raviv , Yael Leibovich Weiss , Omer Cohen , Roy Assa , Guy Katz , Hillel Kugler

Conventional supervised learning methods are often vulnerable to spurious correlations, particularly under distribution shifts in test data. To address this issue, several approaches, most notably Group DRO, have been developed. While these…

Machine Learning · Computer Science 2026-02-13 Sung Ho Jo , Seonghwi Kim , Minwoo Chae

Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem is last-layer…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Mohammad Azizmalayeri , Reza Abbasi , Amir Hosein Haji Mohammad rezaie , Reihaneh Zohrabi , Mahdi Amiri , Mohammad Taghi Manzuri , Mohammad Hossein Rohban

With neural networks being used to control safety-critical systems, they increasingly have to be both accurate (in the sense of matching inputs to outputs) and robust. However, these two properties are often at odds with each other and a…

Systems and Control · Electrical Eng. & Systems 2024-05-30 Ross Drummond , Chris Guiver , Matthew C. Turner

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the…

Machine Learning · Computer Science 2025-10-29 Diego Doimo

Semantic segmentation with fine-grained pixel-level accuracy is a fundamental component of a variety of computer vision applications. However, despite the large improvements provided by recent advances in the architectures of convolutional…

Computer Vision and Pattern Recognition · Computer Science 2020-05-13 Philipe A. Dias , Henry Medeiros

Neural networks are central to many emerging technologies, but verifying their correctness remains a major challenge. It is known that network outputs can be sensitive and fragile to even small input perturbations, thereby increasing the…

Machine Learning · Computer Science 2024-01-09 Anton Xue , Lars Lindemann , Rajeev Alur

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to…

Machine Learning · Computer Science 2019-12-06 Justin Cosentino , Federico Zaiter , Dan Pei , Jun Zhu

In safety-critical deep learning applications robustness measurement is a vital pre-deployment phase. However, existing robustness verification methods are not sufficiently practical for deploying machine learning systems in the real world.…

Machine Learning · Computer Science 2022-07-06 Tianle Zhang , Wenjie Ruan , Jonathan E. Fieldsend

Deep Neural Networks demonstrate exceptional performance but remain vulnerable to adversarial perturbations, necessitating formal verification for safety-critical deployment. To address the computational complexity of this task, researchers…

Software Engineering · Computer Science 2026-03-17 Jingyang Li , Fu Song , Guoqiang Li

Spurious correlation caused by subgroup underrepresentation has received increasing attention as a source of bias that can be perpetuated by deep neural networks (DNNs). Distributionally robust optimization has shown success in addressing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Nilesh Kumar , Ruby Shrestha , Zhiyuan Li , Linwei Wang

Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it…

Machine Learning · Computer Science 2025-07-22 Wenqian Ye , Guangtao Zheng , Aidong Zhang

Although neural networks have been applied to several systems in recent years, they still cannot be used in safety-critical systems due to the lack of efficient techniques to certify their robustness. A number of techniques based on convex…

Machine Learning · Computer Science 2021-09-28 Ziye Ma , Somayeh Sojoudi

Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these…

Machine Learning · Computer Science 2026-04-28 Phuong Quynh Le , Jörg Schlötterer , Christin Seifert

Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks,…

Machine Learning · Statistics 2018-06-04 Nina Narodytska , Shiva Prasad Kasiviswanathan , Leonid Ryzhyk , Mooly Sagiv , Toby Walsh

Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical diagnosis. Unfortunately, state-of-the-art verifiers either…

Machine Learning · Computer Science 2021-05-20 Christoph Müller , François Serre , Gagandeep Singh , Markus Püschel , Martin Vechev

Neural network verification mainly focuses on local robustness properties, which can be checked by bounding the image (set of outputs) of a given input set. However, often it is important to know whether a given property holds globally for…

Software Engineering · Computer Science 2024-01-30 Xiyue Zhang , Benjie Wang , Marta Kwiatkowska

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Leixin Zhou , Wenxiang Deng , Xiaodong Wu