English
Related papers

Related papers: Robustness Certificates Against Adversarial Exampl…

200 papers

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…

Machine Learning · Computer Science 2018-11-08 Tianyu Pang , Chao Du , Yinpeng Dong , Jun Zhu

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

A wide range of verification methods have been proposed to verify the safety properties of deep neural networks ensuring that the networks function correctly in critical applications. However, many well-known verification tools still…

Software Engineering · Computer Science 2023-08-15 Yuyi Zhong , Ruiwei Wang , Siau-Cheng Khoo

Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to not only mislead a…

Machine Learning · Computer Science 2025-11-19 Quoc Viet Vo , Tashreque M. Haq , Paul Montague , Tamas Abraham , Ehsan Abbasnejad , Damith C. Ranasinghe

Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…

Machine Learning · Computer Science 2021-09-08 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…

Machine Learning · Computer Science 2023-05-18 Thomas Altstidl , David Dobre , Björn Eskofier , Gauthier Gidel , Leo Schwinn

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Machine Learning · Statistics 2023-06-02 Dongyoon Yang , Insung Kong , Yongdai Kim

Since graph neural networks (GNNs) are often vulnerable to attack, we need to know when we can trust them. We develop a computationally effective approach towards providing robust certificates for message-passing neural networks (MPNNs)…

Optimization and Control · Mathematics 2024-05-22 Christopher Hojny , Shiqiang Zhang , Juan S. Campos , Ruth Misener

We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. We rely on…

Machine Learning · Computer Science 2021-02-24 Matthew Wicker , Luca Laurenti , Andrea Patane , Zhoutong Chen , Zheng Zhang , Marta Kwiatkowska

The Deep neural networks (DNNs) have achieved great success on a variety of computer vision tasks, however, they are highly vulnerable to adversarial attacks. To address this problem, we propose to improve the local smoothness of the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-23 Yaoyao Zhong , Weihong Deng

Anomaly detection is an important problem in many application areas, such as network security. Many deep learning methods for unsupervised anomaly detection produce good empirical performance but lack theoretical guarantees. By casting…

Machine Learning · Statistics 2024-09-16 Tian-Yi Zhou , Matthew Lau , Jizhou Chen , Wenke Lee , Xiaoming Huo

Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees. However, these techniques can be computationally costly due to the use of certification during training. We…

Machine Learning · Computer Science 2021-02-03 Akhilan Boopathy , Tsui-Wei Weng , Sijia Liu , Pin-Yu Chen , Gaoyuan Zhang , Luca Daniel

Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is…

Machine Learning · Computer Science 2026-03-26 Toby Murray

Adversarial robustness measures the susceptibility of a classifier to imperceptible perturbations made to the inputs at test time. In this work we highlight the benefits of natural low rank representations that often exist for real data…

Machine Learning · Computer Science 2020-08-04 Pranjal Awasthi , Himanshu Jain , Ankit Singh Rawat , Aravindan Vijayaraghavan

Robustness certification against bounded input noise or adversarial perturbations is increasingly important for deployment recurrent neural networks (RNNs) in safety-critical control applications. To address this challenge, we present…

Systems and Control · Electrical Eng. & Systems 2025-09-23 Paul Hamelbeck , Johannes Schiffer

Decision trees are a popular choice of explainable model, but just like neural networks, they suffer from adversarial examples. Existing algorithms for fitting decision trees robust against adversarial examples are greedy heuristics and…

Machine Learning · Computer Science 2021-09-10 Daniël Vos , Sicco Verwer

Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Daqian Shao , Lukas Fesser , Marta Kwiatkowska

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Machine Learning · Computer Science 2022-06-17 Florian Tramèr

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

Machine Learning · Computer Science 2021-01-19 Jia Liu , Yaochu Jin

The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an…

Machine Learning · Computer Science 2023-03-30 Aounon Kumar , Vinu Sankar Sadasivan , Soheil Feizi