English
Related papers

Related papers: Denoised Smoothing: A Provable Defense for Pretrai…

200 papers

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…

Machine Learning · Computer Science 2020-09-29 Giulio Zizzo , Chris Hankin , Sergio Maffeis , Kevin Jones

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Mingkun Zhang , Keping Bi , Wei Chen , Jiafeng Guo , Xueqi Cheng

Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing based defense is a major strategy, as well as learning robust…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Decheng Liu , Tao Chen , Chunlei Peng , Nannan Wang , Ruimin Hu , Xinbo Gao

Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learned…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Samuel Räber , Andreas Plesner , Till Aczel , Roger Wattenhofer

Deep image prior (DIP) is an unsupervised deep learning framework that has been successfully applied to a variety of inverse imaging problems. However, DIP-based methods are inherently prone to overfitting, which leads to performance…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Panagiotis Gkotsis , Athanasios A. Rontogiannis

The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Xuelin Shen , Jiayin Xu , Kangsheng Yin , Wenhan Yang

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Fahad Shamshad , Muzammal Naseer , Karthik Nandakumar

Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. However, existing research primarily focuses on image pre-processing defenses, which often result in reduced classification accuracy…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Nandish Chattopadhyay , Amira Guesmi , Muhammad Shafique

Model attribution is a popular tool to explain the rationales behind model predictions. However, recent work suggests that the attributions are vulnerable to minute perturbations, which can be added to input samples to fool the attributions…

Machine Learning · Computer Science 2024-05-13 Fan Wang , Adams Wai-Kin Kong

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Machine Learning · Computer Science 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied…

Cryptography and Security · Computer Science 2018-01-30 Linh Nguyen , Sky Wang , Arunesh Sinha

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Cryptography and Security · Computer Science 2024-02-13 Raha Moraffah , Shubh Khandelwal , Amrita Bhattacharjee , Huan Liu

Deep neural networks are known to be vulnerable to adversarial attacks. This exposes them to potential exploits in security-sensitive applications and highlights their lack of robustness. This paper uses a variational auto-encoder (VAE) to…

Computer Vision and Pattern Recognition · Computer Science 2018-12-10 Yi Luo , Henry Pfister

Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we…

Cryptography and Security · Computer Science 2019-05-29 Jirong Yi , Hui Xie , Leixin Zhou , Xiaodong Wu , Weiyu Xu , Raghuraman Mudumbai

In this paper, we explore a critical yet under-investigated issue: how to learn robust and well-generalized 3D representation from pre-trained vision language models such as CLIP. Previous works have demonstrated that cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Shuqing Luo , Bowen Qu , Wei Gao

Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier $f$, we show how to construct a new…

Machine Learning · Computer Science 2019-12-17 Grzegorz Głuch , Rüdiger Urbanke

Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or classifier-specific basis. In this work, we take a holistic…

Machine Learning · Computer Science 2020-02-26 Yao-Yuan Yang , Cyrus Rashtchian , Yizhen Wang , Kamalika Chaudhuri

The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-the-art defense…

Machine Learning · Computer Science 2022-08-02 Jay Nandy , Sudipan Saha , Wynne Hsu , Mong Li Lee , Xiao Xiang Zhu

Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifically, it has been…

Cryptography and Security · Computer Science 2024-03-14 Daniel Gibert , Giulio Zizzo , Quan Le

Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO). However, their susceptibility to adversarial examples poses a critical challenge, compromising the reliability…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Weikang Yu , Yonghao Xu , Pedram Ghamisi