English
Related papers

Related papers: Certifiably Robust Interpretation in Deep Learning

200 papers

Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns.…

Machine Learning · Computer Science 2024-11-05 Weizhi Gao , Zhichao Hou , Han Xu , Xiaorui Liu

Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem is NP-hard for decision tree ensembles, hence bound to be…

Machine Learning · Computer Science 2023-11-14 Stefano Calzavara , Lorenzo Cazzaro , Giulio Ermanno Pibiri , Nicola Prezza

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Chong Xiang , Arjun Nitin Bhagoji , Vikash Sehwag , Prateek Mittal

State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks…

Machine Learning · Computer Science 2022-11-17 Ofir Moshe , Gil Fidel , Ron Bitton , Asaf Shabtai

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously manipulate such…

Machine Learning · Computer Science 2023-02-07 Jinghan Yang , Hunmin Kim , Wenbin Wan , Naira Hovakimyan , Yevgeniy Vorobeychik

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

Machine Learning · Computer Science 2019-11-28 Chao Tang , Yifei Fan , Anthony Yezzi

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Machine Learning · Computer Science 2023-05-09 Ambar Pal , Jeremias Sulam

Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-ofthe-art defenses is far from the requirements in critical applications such as…

Machine Learning · Computer Science 2023-06-13 Sravanti Addepalli , Samyak Jain , Gaurang Sriramanan , R. Venkatesh Babu

This paper considers the problem of supervised learning with linear methods when both features and labels can be corrupted, either in the form of heavy tailed data and/or corrupted rows. We introduce a combination of coordinate gradient…

Machine Learning · Statistics 2022-02-01 Stéphane Gaïffas , Ibrahim Merad

Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular…

Machine Learning · Computer Science 2023-10-06 Jonathan Crabbé , Mihaela van der Schaar

Deep Neural Networks (DNNs) have demonstrated exceptional performance on most recognition tasks such as image classification and segmentation. However, they have also been shown to be vulnerable to adversarial examples. This phenomenon has…

Computer Vision and Pattern Recognition · Computer Science 2018-07-10 Anurag Arnab , Ondrej Miksik , Philip H. S. Torr

In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given…

Machine Learning · Statistics 2018-11-07 Amirata Ghorbani , Abubakar Abid , James Zou

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

Machine Learning · Computer Science 2022-03-09 Maria-Florina Balcan , Avrim Blum , Steve Hanneke , Dravyansh Sharma

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Computation and Language · Computer Science 2022-10-28 Jiahao Zhao , Wenji Mao

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

Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic…

Machine Learning · Computer Science 2019-05-13 Fuxun Yu , Zhuwei Qin , Chenchen Liu , Liang Zhao , Yanzhi Wang , Xiang Chen

A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like molecular property prediction or point cloud segmentation have…

Machine Learning · Computer Science 2024-01-17 Jan Schuchardt , Yan Scholten , Stephan Günnemann

Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the…

Machine Learning · Computer Science 2025-06-19 Alaa Anani , Tobias Lorenz , Mario Fritz , Bernt Schiele