English
Related papers

Related papers: StyleFool: Fooling Video Classification Systems vi…

200 papers

Explainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-box models. If the method reveals a significant attribution from a ``protected feature'' (e.g., gender, race) on the model output, the model is…

Machine Learning · Computer Science 2024-08-14 Jun Yuan , Aritra Dasgupta

This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. We propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Marc Treu , Trung-Nghia Le , Huy H. Nguyen , Junichi Yamagishi , Isao Echizen

Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL focuses on tasks like object recognition or detection, which…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Donghyun Kim , Kuniaki Saito , Samarth Mishra , Stan Sclaroff , Kate Saenko , Bryan A Plummer

Deep Learning has been shown to be particularly vulnerable to adversarial samples. To combat adversarial strategies, numerous defensive techniques have been proposed. Among these, a promising approach is to use randomness in order to make…

Cryptography and Security · Computer Science 2020-03-18 Kumar Sharad , Giorgia Azzurra Marson , Hien Thi Thu Truong , Ghassan Karame

Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Anubhav Jain , Yuya Kobayashi , Naoki Murata , Yuhta Takida , Takashi Shibuya , Yuki Mitsufuji , Niv Cohen , Nasir Memon , Julian Togelius

A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Jing Wu , Mingyi Zhou , Shuaicheng Liu , Yipeng Liu , Ce Zhu

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample.…

Machine Learning · Computer Science 2021-02-09 Yigit Alparslan , Ken Alparslan , Jeremy Keim-Shenk , Shweta Khade , Rachel Greenstadt

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer…

Machine Learning · Computer Science 2020-11-11 Lu Wang , Huan Zhang , Jinfeng Yi , Cho-Jui Hsieh , Yuan Jiang

Unrestricted adversarial attacks aim to fool computer vision models without being constrained by $\ell_p$-norm bounds to remain imperceptible to humans, for example, by changing an object's color. This allows attackers to circumvent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Dren Fazlija , Monty-Maximilian Zühlke , Johanna Schrader , Arkadij Orlov , Clara Stein , Iyiola E. Olatunji , Daniel Kudenko

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Tooba Imtiaz , Morgan Kohler , Jared Miller , Zifeng Wang , Masih Eskandar , Mario Sznaier , Octavia Camps , Jennifer Dy

Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show…

Machine Learning · Computer Science 2018-05-22 Yang Song , Taesup Kim , Sebastian Nowozin , Stefano Ermon , Nate Kushman

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Machine Learning · Computer Science 2019-10-23 Saeid Samizade , Zheng-Hua Tan , Chao Shen , Xiaohong Guan

Adversarial images aim to change a target model's decision by minimally perturbing a target image. In the black-box setting, the absence of gradient information often renders this search problem costly in terms of query complexity. In this…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Chuan Guo , Jared S. Frank , Kilian Q. Weinberger

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Kai Hu , Weichen Yu , Li Zhang , Alexander Robey , Andy Zou , Chengming Xu , Haoqi Hu , Matt Fredrikson

Recently, style transfer has received a lot of attention. While much of this research has aimed at speeding up processing, the approaches are still lacking from a principled, art historical standpoint: a style is more than just a single…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Artsiom Sanakoyeu , Dmytro Kotovenko , Sabine Lang , Björn Ommer

Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited due to distribution mismatches between generated adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Yuhao Xue , Zhifei Zhang , Xinyang Jiang , Yifei Shen , Junyao Gao , Wentao Gu , Jiale Zhao , Miaojing Shi , Cairong Zhao

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Machine Learning · Computer Science 2024-10-22 Bar Avraham , Yisroel Mirsky

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Zhaoyu Chen , Bo Li , Shuang Wu , Kaixun Jiang , Shouhong Ding , Wenqiang Zhang

As machine learning models grow in complexity and increasingly rely on publicly sourced data, such as the human-annotated labels used in training large language models, they become more vulnerable to label poisoning attacks. These attacks,…

Machine Learning · Computer Science 2025-02-25 Melis Ilayda Bal , Volkan Cevher , Michael Muehlebach

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto