English
Related papers

Related papers: Minimizing Maximum Model Discrepancy for Transfera…

200 papers

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Ziwen He , Wei Wang , Jing Dong , Tieniu Tan

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

Machine Learning · Computer Science 2025-03-11 Daryna Oliynyk , Rudolf Mayer , Andreas Rauber

The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…

Machine Learning · Computer Science 2025-10-16 Qizhang Li , Yiwen Guo , Xiaochen Yang , Wangmeng Zuo , Hao Chen

Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Hung-Jui Wang , Yu-Yu Wu , Shang-Tse Chen

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

Machine Learning · Computer Science 2023-07-10 Martin Bertran , Shuai Tang , Michael Kearns , Jamie Morgenstern , Aaron Roth , Zhiwei Steven Wu

We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model. Existing black-box…

Machine Learning · Computer Science 2022-06-20 Deokjae Lee , Seungyong Moon , Junhyeok Lee , Hyun Oh Song

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Haibo Zhang , Zhihua Yao , Kouichi Sakurai , Takeshi Saitoh

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Machine Learning · Statistics 2019-11-19 Sanjay Kariyappa , Moinuddin K Qureshi

In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Xiangyuan Yang , Jie Lin , Hanlin Zhang , Xinyu Yang , Peng Zhao

Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial…

Machine Learning · Computer Science 2024-06-13 Feiyang Wang , Xingquan Zuo , Hai Huang , Gang Chen

Much effort has been made to explain and improve the success of transfer-based attacks (TBA) on black-box computer vision models. This work provides the first attempt at a priori prediction of attack success by identifying the presence of…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Ashley S. Dale , Mei Qiu , Foo Bin Che , Thomas Bsaibes , Lauren Christopher , Paul Salama

An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue that transferability is fundamentally related to uncertainty.…

Machine Learning · Computer Science 2022-06-22 Martin Gubri , Maxime Cordy , Mike Papadakis , Yves Le Traon , Koushik Sen

We demonstrate how a target model's generalization gap leads directly to an effective deterministic black box membership inference attack (MIA). This provides an upper bound on how secure a model can be to MIA based on a simple metric.…

Machine Learning · Computer Science 2020-09-15 Jason W. Bentley , Daniel Gibney , Gary Hoppenworth , Sumit Kumar Jha

Adversarial attack methods for 3D point cloud classification reveal the vulnerabilities of point cloud recognition models. This vulnerability could lead to safety risks in critical applications that use deep learning models, such as…

Cryptography and Security · Computer Science 2025-07-30 Ruiyang Zhao , Bingbing Zhu , Chuxuan Tong , Xiaoyi Zhou , Xi Zheng

Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

Machine Learning · Computer Science 2021-05-11 Qi-An Fu , Yinpeng Dong , Hang Su , Jun Zhu

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Xiaoxuan Han , Songlin Yang , Wei Wang , Yang Li , Jing Dong

The emergence of foundational models has greatly improved performance across various downstream tasks, with fine-tuning often yielding even better results. However, existing fine-tuning approaches typically require access to model weights…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Matan Levy , Rami Ben-Ari , Dvir Samuel , Nir Darshan , Dani Lischinski

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Bo Yang , Kaiyong Xu , Hengjun Wang , Hengwei Zhang

By adding human-imperceptible noise to clean images, the resultant adversarial examples can fool other unknown models. Features of a pixel extracted by deep neural networks (DNNs) are influenced by its surrounding regions, and different…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Lianli Gao , Qilong Zhang , Jingkuan Song , Xianglong Liu , Heng Tao Shen

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Siyuan Liang , Longkang Li , Yanbo Fan , Xiaojun Jia , Jingzhi Li , Baoyuan Wu , Xiaochun Cao