English
Related papers

Related papers: Training Meta-Surrogate Model for Transferable Adv…

200 papers

Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting,…

Machine Learning · Computer Science 2022-03-01 Mingyuan Fan , Wenzhong Guo , Shengxing Yu , Zuobin Ying , Ximeng Liu

Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is still challenging to efficiently produce targeted…

Machine Learning · Computer Science 2022-07-25 Xiao Yang , Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

Despite their impressive performance, deep visual models are susceptible to transferable black-box adversarial attacks. Principally, these attacks craft perturbations in a target model-agnostic manner. However, surprisingly, we find that…

Machine Learning · Computer Science 2025-04-15 Mohammad A. A. K. Jalwana , Naveed Akhtar , Ajmal Mian , Nazanin Rahnavard , Mubarak Shah

Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Model Merging (MM) has emerged as a promising alternative to multi-task learning, where multiple fine-tuned models are combined, without access to tasks' training data, into a single model that maintains performance across tasks. Recent…

Machine Learning · Computer Science 2025-09-30 Ankit Gangwal , Aaryan Ajay Sharma

Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…

Machine Learning · Computer Science 2021-12-20 Tianjin Huang , Vlado Menkovski , Yulong Pei , YuHao Wang , Mykola Pechenizkiy

Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are restricted by the availability of an effective surrogate model.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Hashmat Shadab Malik , Shahina K Kunhimon , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

Cryptography and Security · Computer Science 2020-04-01 Mingyi Zhou , Jing Wu , Yipeng Liu , Xiaolin Huang , Shuaicheng Liu , Xiang Zhang , Ce Zhu

We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and training datasets. This scenario significantly differs from…

Machine Learning · Computer Science 2021-03-19 Nathan Inkawhich , Kevin J Liang , Jingyang Zhang , Huanrui Yang , Hai Li , Yiran Chen

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…

Machine Learning · Computer Science 2018-11-22 Qian Huang , Zeqi Gu , Isay Katsman , Horace He , Pian Pawakapan , Zhiqiu Lin , Serge Belongie , Ser-Nam Lim

Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…

Computer Vision and Pattern Recognition · Computer Science 2020-03-04 ZhaoXin Huan , Yulong Wang , Xiaolu Zhang , Lin Shang , Chilin Fu , Jun Zhou

Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. An alarming side-effect of evasion attacks is their ability to transfer among different models: this…

Cryptography and Security · Computer Science 2023-06-28 Marco Alecci , Mauro Conti , Francesco Marchiori , Luca Martinelli , Luca Pajola

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…

Machine Learning · Computer Science 2020-03-02 Qian Huang , Isay Katsman , Horace He , Zeqi Gu , Serge Belongie , Ser-Nam Lim

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Chen Ma , Li Chen , Jun-Hai Yong

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…

Machine Learning · Computer Science 2021-09-28 Luke E. Richards , André Nguyen , Ryan Capps , Steven Forsythe , Cynthia Matuszek , Edward Raff

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yao Zhu , Yuefeng Chen , Xiaodan Li , Kejiang Chen , Yuan He , Xiang Tian , Bolun Zheng , Yaowu Chen , Qingming Huang

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Machine Learning · Computer Science 2019-06-11 Anshuman Chhabra , Abhishek Roy , Prasant Mohapatra

A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and…

Machine Learning · Computer Science 2022-03-17 Nicholas A. Lord , Romain Mueller , Luca Bertinetto

Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require the target model's…

Cryptography and Security · Computer Science 2025-04-21 CheolWon Na , YunSeok Choi , Jee-Hyong Lee