Skip to Content

728 Results Found

  • Article
  • Open Access
1 Citations
1,484 Views
13 Pages

20 September 2025

Adversarial attacks against deep learning models achieve high performance in white-box settings but often exhibit low transferability in black-box scenarios, especially against defended models. In this work, we propose Multi-Path Random Restart (MPRR...

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security: Trends and Challenges)
  • Article
  • Open Access
565 Views
18 Pages

Leveraging Attack Non-Transferability to Boost Adversarial Robustness for Foundation Models

  • Koshiro Toishi,
  • Keisuke Maeda,
  • Ren Togo,
  • Takahiro Ogawa and
  • Miki Haseyama

17 April 2026

This paper presents a novel adversarial defense framework that strategically exploits the non-transferability of adversarial attacks across multi-modal foundation models. While Contrastive Language–Image Pre-training (CLIP) models demonstrate r...

  • Article
  • Open Access
7 Citations
3,402 Views
15 Pages

Enhance Domain-Invariant Transferability of Adversarial Examples via Distance Metric Attack

  • Jin Zhang,
  • Wenyu Peng,
  • Ruxin Wang,
  • Yu Lin and ,
  • Wei Zhou and
  • Ge Lan
  • + 1 author+ 0 author

11 April 2022

A general foundation of fooling a neural network without knowing the details (i.e., black-box attack) is the attack transferability of adversarial examples across different models. Many works have been devoted to enhancing the task-specific transfera...

(This article belongs to the Topic Machine and Deep Learning)
  • Article
  • Open Access
486 Views
14 Pages

8 May 2026

Most adversarial attack methods achieve high success rates under the white-box setting. However, these methods often lack transferability when targeting other deep neural network (DNN) models. Momentum-based attacks have emerged as an effective strat...

  • Article
  • Open Access
340 Views
37 Pages

No-reference image quality assessment (NR-IQA) metrics are widely used to evaluate and train image and video processing algorithms, but the growing reliance on deep neural networks makes these metrics vulnerable to adversarial attacks. Among such att...

  • Article
  • Open Access
953 Views
23 Pages

11 April 2026

Adversarial examples have revealed the vulnerability of deep neural networks, and their transferability makes black-box attacks particularly concerning. However, perturbations crafted on a surrogate model often do not remain sufficiently effective on...

  • Article
  • Open Access
637 Views
25 Pages

19 April 2026

Adversarial examples reveal critical vulnerabilities in deep neural networks, posing significant risks in real-world deployment. In black-box settings, transferable targeted attacks rely on surrogate models but often suffer from low success rates. We...

(This article belongs to the Special Issue Advanced Research in Neural Networks, Machine Learning, and Image Processing)
  • Article
  • Open Access
3 Citations
2,615 Views
11 Pages

Enhancing the Transferability of Targeted Attacks with Adversarial Perturbation Transform

  • Zhengjie Deng,
  • Wen Xiao,
  • Xiyan Li,
  • Shuqian He and
  • Yizhen Wang

15 September 2023

The transferability of adversarial examples has been proven to be a potent tool for successful attacks on target models, even in challenging black-box environments. However, the majority of current research focuses on non-targeted attacks, making it...

  • Article
  • Open Access
526 Views
25 Pages

SAGE: Saliency and Geometry Enhanced Transferable Attacks for LiDAR Point Cloud Perception in Remote Sensing

  • Yuheng Wu,
  • Shiwei Lin,
  • Shibo Ping,
  • Xingchao Zhai and ,
  • Zhiyuan Fang,
  • Meijuan Chen and
  • Weiquan Liu
  • + 2 authors+ 0 author

5 July 2026

LiDAR point clouds are widely used in remote sensing perception scenarios, such as autonomous driving. However, LiDAR-based perception models remain vulnerable to adversarial perturbations, which may compromise the reliability of safety-critical 3D p...

(This article belongs to the Special Issue Intelligent Processing of 3D Point Clouds for Scene Understanding and Modelling)
  • Article
  • Open Access
4 Citations
2,651 Views
20 Pages

25 November 2024

The study of LiDAR-based 3D object detection and its robustness under adversarial attacks has achieved great progress. However, existing adversarial attack methods mainly focus on the targeted object, which destroys the integrity of the object and ma...

(This article belongs to the Special Issue Artificial Intelligence-Based Sensor Data Processing for Remote Sensing)
  • Article
  • Open Access
1,649 Views
14 Pages

Improving Transferability of Adversarial Attacks via Maximization and Targeting from Image to Video Quality Assessment

  • Georgii Gotin,
  • Ekaterina Shumitskaya,
  • Dmitriy Vatolin and
  • Anastasia Antsiferova

This paper proposes a novel method for transferable adversarial attacks from Image Quality Assessment (IQA) to Video Quality Assessment (VQA) models. Attacking modern VQA models is challenging due to their high complexity and the temporal nature of v...

  • Article
  • Open Access
21 Citations
3,478 Views
23 Pages

Boosting Adversarial Transferability with Shallow-Feature Attack on SAR Images

  • Gengyou Lin,
  • Zhisong Pan,
  • Xingyu Zhou,
  • Yexin Duan and ,
  • Wei Bai,
  • Dazhi Zhan,
  • Leqian Zhu,
  • Gaoqiang Zhao and
  • Tao Li
  • + 4 authors+ 0 author

22 May 2023

Adversarial example generation on Synthetic Aperture Radar (SAR) images is an important research area that could have significant impacts on security and environmental monitoring. However, most current adversarial attack methods on SAR images are des...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
1 Citations
881 Views
17 Pages

1 May 2026

DNNs are highly vulnerable to adversarial examples (AEs). To achieve high transferability, traditional AEs often introduce unnatural artifacts that are easily perceptible to the human eye. Unrestricted attacks have emerged as a promising paradigm to...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
449 Views
16 Pages

24 July 2026

Point cloud perception is important in autonomous driving, robotics, and other security-critical 3D systems, yet learned point cloud classifiers remain vulnerable to transferable adversarial perturbations. A central difficulty in transfer-based black...

(This article belongs to the Special Issue Security, Privacy and Application in New Intelligence Techniques: 2nd Edition)
  • Article
  • Open Access
19 Views
37 Pages

MIST: Multi-Source Imperceptible Saliency-Guided Transferable Adversarial Attack Framework for LiDAR Point Cloud Perception in Remote Sensing

  • Shibo Ping,
  • Penghao Lin,
  • Shixin Hong,
  • Zhiwei Li and ,
  • Yuan Fang,
  • Qijin Lin,
  • Jingyan Li,
  • Xingchao Zhai,
  • Shuyou Pang and
  • Weiquan Liu
  • + 6 authors+ 1 author

15 November 2026

LiDAR is an important remote sensing technology for acquiring three-dimensional spatial information, providing data for object identification, localization, and scene understanding in applications such as autonomous driving. As these systems rely on...

(This article belongs to the Section AI Remote Sensing)
  • Article
  • Open Access
13 Citations
2,904 Views
15 Pages

ResADM: A Transfer-Learning-Based Attack Detection Method for Cyber–Physical Systems

  • Huan Wang,
  • Haifeng Zhang,
  • Lei Zhu,
  • Yan Wang and
  • Junyi Deng

6 December 2023

Deep learning has proven to be effective for enhancing the accuracy and efficiency of attack detection through training with large sample sizes. However, when applied to cyber–physical systems (CPSs), it still encounters challenges such as scar...

(This article belongs to the Special Issue Advances in Attack Detection and Secure State Estimation for Cyber–Physical Systems (CPS))
  • Article
  • Open Access
9 Citations
4,262 Views
16 Pages

Robustness and Transferability of Adversarial Attacks on Different Image Classification Neural Networks

  • Kamilya Smagulova,
  • Lina Bacha,
  • Mohammed E. Fouda,
  • Rouwaida Kanj and
  • Ahmed Eltawil

Recent works demonstrated that imperceptible perturbations to input data, known as adversarial examples, can mislead neural networks’ output. Moreover, the same adversarial sample can be transferable and used to fool different neural models. Su...

  • Article
  • Open Access
591 Views
25 Pages

1 July 2026

Deep neural networks have substantially improved the performance of hyperspectral image classification, yet they remain vulnerable to adversarial attacks. Existing attack methods usually manipulate pixel spectra directly, ignoring the physical mixing...

(This article belongs to the Special Issue Remote Sensing Target Recognition and Detection: Theory and Applications (Second Edition))
  • Article
  • Open Access
8 Citations
4,386 Views
9 Pages

8 December 2022

Backdoor attacks are a serious security threat to open-source and outsourced development of computational systems based on deep neural networks (DNNs). In particular, the transferability of backdoors is remarkable; that is, they can remain effective...

(This article belongs to the Special Issue Advances in Secure AI: Technology and Applications)
  • Article
  • Open Access
861 Views
22 Pages

LatAtk: A Medical Image Attack Method Focused on Lesion Areas with High Transferability

  • Long Li,
  • Yibo Huang,
  • Chong Li,
  • Fei Zhou and ,
  • Jingjing Li and
  • Kamarul Hawari Ghazali
  • + 1 author+ 0 author

11 November 2025

The rise in trusted machine learning has prompted concerns about the security, reliability and controllability of deep learning, especially when it is applied to sensitive areas involving life and health safety. To thoroughly analyze potential attack...

(This article belongs to the Section Medical Imaging)
  • Article
  • Open Access
3 Citations
2,734 Views
15 Pages

8 December 2024

Physical adversarial attacks face significant challenges in achieving transferability across different object detection models, especially in real-world conditions. This is primarily due to variations in model architectures, training data, and detect...

  • Article
  • Open Access
364 Views
28 Pages

4 July 2026

Deepneural networks are highly vulnerable to adversarial examples, which are generated by introducing subtle perturbations to input data to mislead model classification. Currently, transfer-based attacks are prevalent in adversarial example generatio...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
12 Citations
3,097 Views
18 Pages

At present, deep neural networks have been widely used in various fields, but their vulnerability requires attention. The adversarial attack aims to mislead the model by generating imperceptible perturbations on the source model, and although white-b...

(This article belongs to the Special Issue AI in Knowledge-Based Information and Decision Support Systems)
  • Article
  • Open Access
5 Citations
3,683 Views
20 Pages

Transferable Targeted Adversarial Attack on Synthetic Aperture Radar (SAR) Image Recognition

  • Sheng Zheng,
  • Dongshen Han,
  • Chang Lu,
  • Chaowen Hou and ,
  • Yanwen Han,
  • Xinhong Hao and
  • Chaoning Zhang
  • + 2 authors+ 0 author

3 January 2025

Deep learning models have been widely applied to synthetic aperture radar (SAR) target recognition, offering end-to-end feature extraction that significantly enhances recognition performance. However, recent studies show that optical image recognitio...

(This article belongs to the Special Issue Advanced Artificial Intelligence and Deep Learning for Remote Sensing II)
  • Article
  • Open Access
23 Citations
5,024 Views
15 Pages

4 February 2022

Transfer learning from natural images is used in deep neural networks (DNNs) for medical image classification to achieve a computer-aided clinical diagnosis. Although the adversarial vulnerability of DNNs hinders practical applications owing to the h...

  • Article
  • Open Access
636 Views
21 Pages

DPSF: A Dynamic Patch Shape Selection Framework for Cross-Model Transferable Adversarial Attacks

  • Han Zhang,
  • Boqi Huang,
  • Bingshu Wang,
  • Laixian Zhang and ,
  • Aihong Shangguan and
  • Haosu Zhang
  • + 1 author+ 0 author

22 July 2026

Adversarial patch attacks are core tools to evaluate adversarial robustness in remote sensing image classification, yet existing methods with fixed patch shapes and single-model optimization yield poor cross-architecture black-box transferability. Th...

(This article belongs to the Special Issue Information Acquisition and Processing for Remote Sensing (IAP-RS))
  • Article
  • Open Access
637 Views
20 Pages

Adversarial attacks have been extensively studied in recent years to investigate the vulnerability mechanisms of deep neural networks and enhance model robustness and security. However, the transferability of adversarial examples across different mod...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
4 Citations
3,150 Views
16 Pages

4 November 2023

Cybersecurity faces constant challenges from increasingly sophisticated network attacks. Recent research shows machine learning can improve attack detection by training models on large labeled datasets. However, obtaining sufficient labeled data is d...

(This article belongs to the Special Issue New Insights and Perspectives in Cyber and Information Security)
  • Article
  • Open Access
11 Citations
3,971 Views
19 Pages

26 September 2023

Website fingerprinting attacks attempt to apply deep learning technology to identify websites corresponding to encrypted traffic data. Unfortunately, to the best of our knowledge, once the total number of encrypted traffic data becomes insufficient,...

(This article belongs to the Special Issue Privacy-Preserving Techniques in AI, Blockchain and Cloud Systems with Formal Mathematical Analysis)
  • Article
  • Open Access
13 Citations
6,126 Views
32 Pages

Transfer and CNN-Based De-Authentication (Disassociation) DoS Attack Detection in IoT Wi-Fi Networks

  • Samson Kahsay Gebresilassie,
  • Joseph Rafferty,
  • Liming Chen,
  • Zhan Cui and
  • Mamun Abu-Tair

4 September 2023

The Internet of Things (IoT) is a network of billions of interconnected devices embedded with sensors, software, and communication technologies. Wi-Fi is one of the main wireless communication technologies essential for establishing connections and f...

(This article belongs to the Special Issue Communication, Sensing and Computing for Intelligent Internet of Things Enabled Applications)
  • Article
  • Open Access
1,889 Views
14 Pages

30 April 2024

Existing textual attacks mostly perturb keywords in sentences to generate adversarial examples by relying on the prediction confidence of victim models. In practice, attackers can only access the prediction label, meaning that the victim model can ea...

(This article belongs to the Special Issue Innovative Applications of Artificial Intelligence in Multidisciplinary Sciences: Latest Advances and Prospects)
  • Article
  • Open Access
5 Citations
2,513 Views
20 Pages

TL-Efficient-SE: A Transfer Learning-Based Attention-Enhanced Model for Fingerprint Liveness Detection Across Multi-Sensor Spoof Attacks

  • Archana Pallakonda,
  • Rayappa David Amar Raj,
  • Rama Muni Reddy Yanamala,
  • Christian Napoli and
  • Cristian Randieri

Fingerprint authentication systems encounter growing threats from presentation attacks, making strong liveness detection crucial. This work presents a deep learning-based framework integrating EfficientNetB0 with a Squeeze-and-Excitation (SE) attenti...

(This article belongs to the Special Issue Advances in Machine and Deep Learning)
  • Article
  • Open Access
543 Views
18 Pages

AMGAA: Attention-Guided Multi-Target Generative Adversarial Attack for Vision Transformers

  • Dongbo Ou,
  • Jintian Lu,
  • Shihui Zhou,
  • Ying Zeng and ,
  • Dongwan Liao,
  • Haoyin Liu,
  • Chao Yang,
  • Yingsheng He and
  • Jie Tian
  • + 4 authors+ 0 author

12 June 2026

Vision Transformers (ViTs) have achieved strong performance in computer vision, but their adversarial robustness remains underexplored. Existing ViT-oriented attacks mainly rely on iterative optimization, leading to high generation cost and limited t...

  • Article
  • Open Access
5 Citations
2,883 Views
16 Pages

24 October 2024

Adversarial attacks that mislead deep neural networks (DNNs) into making incorrect predictions can also be implemented in the physical world. However, most of the existing adversarial camouflage textures that attack object detection models only consi...

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity)
  • Article
  • Open Access
14 Citations
3,704 Views
21 Pages

TAN: A Transferable Adversarial Network for DNN-Based UAV SAR Automatic Target Recognition Models

  • Meng Du,
  • Yuxin Sun,
  • Bing Sun,
  • Zilong Wu and ,
  • Lan Luo,
  • Daping Bi and
  • Mingyang Du
  • + 2 authors+ 0 author

16 March 2023

Recently, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based o...

(This article belongs to the Special Issue When Deep Learning Meets Geometry for Air-to-Ground Perception on Drones)
  • Article
  • Open Access
3 Citations
3,466 Views
27 Pages

21 July 2022

Through the addition of humanly imperceptible noise to an image classified as belonging to a category ca, targeted adversarial attacks can lead convolutional neural networks (CNNs) to classify a modified image as belonging to any predefined target cl...

(This article belongs to the Special Issue Explainable Artificial Intelligence (XAI))
  • Article
  • Open Access
1 Citations
505 Views
20 Pages

Decoupling the Dual Impact of NISQ Noise on Quantum Adversarial Robustness

  • Haoran Wang,
  • Shaoliang Ye,
  • Shaowei Wang,
  • Hanyi Wang and ,
  • Zhenbo Shi and
  • Wei Yang
  • + 1 author+ 0 author

24 June 2026

As quantum machine learning modules become increasingly integrated into NISQ-era infrastructures, it remains unclear whether intrinsic device noise can be regarded as a passive defense against adversarial examples, or whether it in fact introduces a...

(This article belongs to the Special Issue Quantum Information Security)
  • Article
  • Open Access
1 Citations
732 Views
23 Pages

Audio deepfake and vocoder fingerprint detectors are increasingly used to identify synthetic speech and attribute it to its generating model. However, their robustness against adversarial perturbations remains unclear across attack algorithms, pertur...

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security)
  • Article
  • Open Access
1,285 Views
21 Pages

Adversarial Example Generation Method Based on Wavelet Transform

  • Meng Bi,
  • Xiaoguo Liang,
  • Baiyu Wang,
  • Longxin Liu and ,
  • Xin Yin and
  • Jiafeng Liu
  • + 1 author+ 0 author

10 February 2026

Adversarial examples are crucial tools for assessing the robustness of deep neural networks (DNNs) and revealing potential security vulnerabilities. Adversarial example generation methods based on Generative Adversarial Networks (GANs) have made sign...

  • Article
  • Open Access
2 Citations
2,689 Views
16 Pages

21 August 2023

Over the past decade, Convolutional Neural Networks (CNNs) have been extensively deployed in security-critical areas; however, the security of CNN models is threatened by adversarial attacks. Decision-based adversarial attacks, wherein an attacker re...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
19 Citations
3,567 Views
16 Pages

Boosting Adversarial Attacks with Nadam Optimizer

  • Qikun Zhang,
  • Yuzhi Zhang,
  • Yanling Shao,
  • Mengqi Liu and ,
  • Jianyong Li,
  • Junling Yuan and
  • Ruifang Wang
  • + 2 authors+ 0 author

Deep neural networks are extremely vulnerable to attacks and threats from adversarial examples. These adversarial examples deliberately crafted by attackers can easily fool classification models by adding imperceptibly tiny perturbations on clean ima...

(This article belongs to the Special Issue AI-Driven Network Security and Privacy)
  • Article
  • Open Access
1 Citations
3,871 Views
23 Pages

A Local Adversarial Attack with a Maximum Aggregated Region Sparseness Strategy for 3D Objects

  • Ling Zhao,
  • Xun Lv,
  • Lili Zhu,
  • Binyan Luo and ,
  • Hang Cao,
  • Jiahao Cui,
  • Haifeng Li and
  • Jian Peng
  • + 3 authors+ 0 author

13 January 2025

The increasing reliance on deep neural network-based object detection models in various applications has raised significant security concerns due to their vulnerability to adversarial attacks. In physical 3D environments, existing adversarial attacks...

  • Review
  • Open Access
3 Citations
4,057 Views
34 Pages

29 October 2025

Deep neural networks have demonstrated remarkable performance in object detection tasks; however, they remain highly susceptible to adversarial attacks. Previous surveys in computer vision have provided considerable coverage of physical adversarial a...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
4 Citations
1,988 Views
24 Pages

10 July 2024

Recent research has revealed that the deep neural network (DNN)-based synthetic-aperture radar (SAR) automatic target recognition (ATR) techniques are vulnerable to adversarial examples, which poses significant security risks for their deployment in...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
1,005 Views
24 Pages

19 December 2025

Remote sensing plays a critical role in environmental monitoring, land use analysis, and disaster response by enabling large-scale, data-driven observation of Earth’s surface. Image classification models are central to interpreting remote sensi...

  • Article
  • Open Access
397 Views
16 Pages

Color Adversarial Patch Generation for Physical-Domain Palmprint Recognition Attacks

  • Yue Liu,
  • Qi Xiong,
  • Lu Leng,
  • Cheonshik Kim and ,
  • Jun Miao and
  • Lu Wang
  • + 1 author+ 0 author

21 August 2026

Physical-domain adversarial attacks have been extensively studied in face recognition and object detection, yet the field of palmprint recognition remains largely unexplored. Existing methods generate grayscale patches constrained by the single-chann...

  • Article
  • Open Access
5 Citations
4,782 Views
12 Pages

14 February 2020

Forced convection heat transfer is a significant factor for the thermal control of a stratospheric airship. However, most of researches were conducted without considering the influence of flight state causing serious errors. In order to accurately pr...

(This article belongs to the Section Energy Science and Technology)
  • Article
  • Open Access
1 Citations
1,196 Views
26 Pages

Physics-Aware Spatiotemporal Consistency for Transferable Defense of Autonomous Driving Perception

  • Yang Liu,
  • Zishan Nie,
  • Tong Yu,
  • Minghui Chen and ,
  • Zhiheng Yao,
  • Jieke Lu,
  • Linya Peng and
  • Fuming Fan
  • + 3 authors+ 0 author

27 January 2026

Autonomous driving perception systems are vulnerable to physical adversarial attacks. Existing defenses largely adopt loosely coupled architectures where visual and kinematic cues are processed in isolation, thus failing to exploit physical spatiotem...

(This article belongs to the Special Issue Advanced Sensor Technologies for Multimodal Decision-Making)
  • Article
  • Open Access
3 Citations
1,490 Views
23 Pages

2 October 2025

In today’s digital era, cyberattacks are rapidly evolving, rendering traditional security mechanisms increasingly inadequate. The adoption of AI-based Network Intrusion Detection Systems (NIDS) has emerged as a promising solution, due to their...

(This article belongs to the Special Issue Security and Privacy Technologies in Smart Cities: Advances in Anomaly Detection and Privacy-Preserving Solutions)
  • Article
  • Open Access
1 Citations
708 Views
34 Pages

BUM: Bayesian Uncertainty Minimization for Transferable Adversarial Examples in SAR Recognition

  • Hongqiang Wang,
  • Yuqing Lan,
  • Fuzhan Yue,
  • Zhenghuan Xia and
  • Tao Zhang

26 February 2026

Adversarial examples pose a significant threat to Deep Neural Networks (DNNs) underpinning Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems, as these models exhibit acute susceptibility to such malicious inputs. While white-b...

(This article belongs to the Special Issue Advanced Artificial Intelligence and Deep Learning for Remote Sensing (3rd Edition))

of 15