English
Related papers

Related papers: Towards More Robust Interpretation via Local Gradi…

200 papers

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Machine Learning · Computer Science 2019-02-25 Gavin Weiguang Ding , Kry Yik Chau Lui , Xiaomeng Jin , Luyu Wang , Ruitong Huang

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Machine Learning · Computer Science 2025-02-10 Binghui Li , Yuanzhi Li

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Tejas Gokhale , Rushil Anirudh , Bhavya Kailkhura , Jayaraman J. Thiagarajan , Chitta Baral , Yezhou Yang

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our…

Machine Learning · Computer Science 2020-02-19 Milad Alizadeh , Arash Behboodi , Mart van Baalen , Christos Louizos , Tijmen Blankevoort , Max Welling

Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data. However, achieving…

Machine Learning · Computer Science 2023-05-25 Gorana Gojić , Vladimir Vincan , Ognjen Kundačina , Dragiša Mišković , Dinu Dragan

We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training problem as a joint optimization problem with both empirical…

Machine Learning · Computer Science 2021-06-08 Jiameng Fan , Wenchao Li

Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training,…

Machine Learning · Computer Science 2025-09-09 Vincent-Daniel Yun

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical…

Machine Learning · Statistics 2018-12-06 Timothy E. Wang , Yiming Gu , Dhagash Mehta , Xiaojun Zhao , Edgar A. Bernal

In many classification problems a classifier should be robust to small variations in the input vector. This is a desired property not only for particular transformations, such as translation and rotation in image classification problems,…

Machine Learning · Statistics 2016-01-18 Sergey Demyanov , James Bailey , Ramamohanarao Kotagiri , Christopher Leckie

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

Image and Video Processing · Electrical Eng. & Systems 2021-06-14 Mohammad Zalbagi Darestani , Akshay S. Chaudhari , Reinhard Heckel

Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network…

Computation and Language · Computer Science 2016-09-21 Yitong Li , Trevor Cohn , Timothy Baldwin

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

Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. However, symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and…

Machine Learning · Computer Science 2023-10-11 Tycho F. A. van der Ouderaa , Alexander Immer , Mark van der Wilk

Model attributions are important in deep neural networks as they aid practitioners in understanding the models, but recent studies reveal that attributions can be easily perturbed by adding imperceptible noise to the input. The…

Machine Learning · Computer Science 2022-09-27 Fan Wang , Adams Wai-Kin Kong

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Apostolos Modas

Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net…

Machine Learning · Computer Science 2017-06-19 Osbert Bastani , Yani Ioannou , Leonidas Lampropoulos , Dimitrios Vytiniotis , Aditya Nori , Antonio Criminisi

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…

Machine Learning · Computer Science 2019-12-05 Varun Chandrasekaran , Brian Tang , Nicolas Papernot , Kassem Fawaz , Somesh Jha , Xi Wu

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input…

Computer Vision and Pattern Recognition · Computer Science 2019-06-17 Houpu Yao , Zhe Wang , Guangyu Nie , Yassine Mazboudi , Yezhou Yang , Yi Ren

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs…

Machine Learning · Computer Science 2019-04-22 Beomsu Kim , Junghoon Seo , Taegyun Jeon

Three important criteria of existing convolutional neural networks (CNNs) are (1) test-set accuracy; (2) out-of-distribution accuracy; and (3) explainability. While these criteria have been studied independently, their relationship is…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Mehdi Nourelahi , Lars Kotthoff , Peijie Chen , Anh Nguyen