English
Related papers

Related papers: AFD: Mitigating Feature Gap for Adversarial Robust…

200 papers

The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangling feature representations rely on the presence of many…

Machine Learning · Computer Science 2017-11-28 Ershad Banijamali , Amir-Hossein Karimi , Alexander Wong , Ali Ghodsi

Adversarial examples cause neural networks to produce incorrect outputs with high confidence. Although adversarial training is one of the most effective forms of defense against adversarial examples, unfortunately, a large gap exists…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Saehyung Lee , Hyungyu Lee , Sungroh Yoon

This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called DifAttack, which…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Liu Jun , Zhou Jiantao , Zeng Jiandian , Jinyu Tian

We consider the disentanglement of the representations of the relevant attributes of the data (content) from all other factors of variations (style) using Variational Autoencoders. Some recent works addressed this problem by utilizing…

Machine Learning · Computer Science 2020-01-15 Jozsef Nemeth

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…

Machine Learning · Computer Science 2025-08-26 Quanwei Wu , Jun Guo , Wei Wang , Yi Wang

The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via…

Computer Vision and Pattern Recognition · Computer Science 2017-09-13 Lingxiao Song , Man Zhang , Xiang Wu , Ran He

Recently, it has been widely known that deep neural networks are highly vulnerable and easily broken by adversarial attacks. To mitigate the adversarial vulnerability, many defense algorithms have been proposed. Recently, to improve…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Hong Joo Lee , Yong Man Ro

An adaptive refinement strategy, based on an equilibrated flux a posteriori error estimator, is proposed in the context of defeaturing problems. Defeaturing consists of removing features from complex domains to simplify mesh generation and…

Numerical Analysis · Mathematics 2026-03-04 Annalisa Buffa , Denise Grappein , Rafael Vázquez

Feature Squeezing is a recently proposed defense method which reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. It has been…

Machine Learning · Statistics 2018-03-28 Yash Sharma , Pin-Yu Chen

While deep neural networks have been achieving state-of-the-art performance across a wide variety of applications, their vulnerability to adversarial attacks limits their widespread deployment for safety-critical applications. Alongside…

Computer Vision and Pattern Recognition · Computer Science 2020-03-04 Ahmadreza Jeddi , Mohammad Javad Shafiee , Michelle Karg , Christian Scharfenberger , Alexander Wong

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

Machine Learning · Computer Science 2020-11-06 Calvin Luo , Hossein Mobahi , Samy Bengio

Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Nuoyan Zhou , Nannan Wang , Decheng Liu , Dawei Zhou , Xinbo Gao

A method based on Generative Adversaria! Networks (GANs) is developed for disentangling the physical (effective temperature and gravity) and chemical (metallicity, overabundance of a-elements with respect to iron) atmospheric properties in…

Instrumentation and Methods for Astrophysics · Physics 2025-02-26 Minia Manteiga , Raúl Santoveña , Marco A. Álvarez , Carlos Dafonte , Manuel G. Penedo , Silvana Navarro , Luis Corral

Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Jiangwei Zhao , Zejia Liu , Xiaohan Guo , Lili Pan

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Xianyi Chen , Fazhan Liu , Dong Jiang , Kai Yan

With the development of high-throughput technologies, genomics datasets rapidly grow in size, including functional genomics data. This has allowed the training of large Deep Learning (DL) models to predict epigenetic readouts, such as…

Genomics · Quantitative Biology 2024-05-30 Alexander Rakowski , Remo Monti , Viktoriia Huryn , Marta Lemanczyk , Uwe Ohler , Christoph Lippert

Due to scene complexity, sensor inaccuracies, and processing imprecision, point cloud corruption is inevitable. Over-reliance on input features is the root cause of DNN vulnerabilities. It remains unclear whether this issue exists in 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zhiqiang Tian , Weigang Li , Chunhua Deng , Junwei Hu , Yongqiang Wang , Wenping Liu

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Shuo Wang , Lingjuan Lyu , Surya Nepal , Carsten Rudolph , Marthie Grobler , Kristen Moore

Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these…

Machine Learning · Computer Science 2023-12-07 Jae Young Lee , Wonjun Lee , Jaehyun Choi , Yongkwi Lee , Young Seog Yoon