Skip to Content

6,455 Results Found

  • Article
  • Open Access
734 Views
27 Pages

7 April 2026

As AI-driven educational systems increasingly rely on deep neural networks, their vulnerability to adversarial perturbations raises concerns about assessment integrity, fairness, and reliability. Adversarial example purification is attractive for suc...

(This article belongs to the Special Issue Artificial Intelligence Technologies for Education: Advancements, Challenges, and Impacts, 2nd Edition)
  • Article
  • Open Access
42 Citations
6,018 Views
20 Pages

29 October 2021

Some recent articles have revealed that synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep learning are vulnerable to the attacks of adversarial examples and cause security problems. The adversarial attack can make a...

  • Article
  • Open Access
5 Citations
5,998 Views
14 Pages

Transformer-based models are driving a significant revolution in the field of machine learning at the moment. Among these innovations, vision transformers (ViTs) stand out for their application of transformer architectures to vision-related tasks. By...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
33 Citations
5,867 Views
16 Pages

14 November 2020

State-of-the-art neural network models are actively used in various fields, but it is well-known that they are vulnerable to adversarial example attacks. Throughout the efforts to make the models robust against adversarial example attacks, it has bee...

  • Article
  • Open Access
2 Citations
2,144 Views
24 Pages

Triple Down on Robustness: Understanding the Impact of Adversarial Triplet Compositions on Adversarial Robustness

  • Sander Joos,
  • Tim Van hamme,
  • Willem Verheyen,
  • Davy Preuveneers and
  • Wouter Joosen

Adversarial training, a widely used technique for fortifying the robustness of machine learning models, has seen its effectiveness further bolstered by modifying loss functions or incorporating additional terms into the training objective. While thes...

(This article belongs to the Collection Extravaganza Feature Papers on Hot Topics in Machine Learning and Knowledge Extraction)
  • Article
  • Open Access
6 Citations
3,749 Views
17 Pages

31 July 2023

While Machine Learning has become the holy grail of modern-day computing, it has many security flaws that have yet to be addressed and resolved. Adversarial attacks are one of these security flaws, in which an attacker appends noise to data samples t...

(This article belongs to the Special Issue Generative Models in Artificial Intelligence and Their Applications II)
  • Article
  • Open Access
14 Citations
7,996 Views
15 Pages

In this work, we propose a novel defense system against adversarial examples leveraging the unique power of Generative Adversarial Networks (GANs) to generate new adversarial examples for model retraining. To do so, we develop an automated pipeline u...

(This article belongs to the Special Issue Big Data and Cognitive Computing: Feature Papers 2020)
  • Article
  • Open Access
122 Citations
10,104 Views
21 Pages

Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

  • Sheeba Lal,
  • Saeed Ur Rehman,
  • Jamal Hussain Shah,
  • Talha Meraj and ,
  • Hafiz Tayyab Rauf,
  • Robertas Damaševičius,
  • Mazin Abed Mohammed and
  • Karrar Hameed Abdulkareem
  • + 3 authors+ 0 author

7 June 2021

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been...

(This article belongs to the Special Issue Deep Learning Image Recognition Systems)
  • Article
  • Open Access
4 Citations
4,496 Views
19 Pages

Enhancing Adversarial Robustness through Stable Adversarial Training

  • Kun Yan,
  • Luyi Yang,
  • Zhanpeng Yang and
  • Wenjuan Ren

14 October 2024

Deep neural network models are vulnerable to attacks from adversarial methods, such as gradient attacks. Evening small perturbations can cause significant differences in their predictions. Adversarial training (AT) aims to improve the model’s a...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
426 Views
37 Pages

5 October 2026

The growing vulnerability of computer vision models to adversarial attacks has raised great concerns about the reliability of generative models in security-sensitive applications. Quantum generative models show strong potential for learning complex d...

(This article belongs to the Section Quantum Information)
  • Article
  • Open Access
8 Citations
3,014 Views
21 Pages

Perspectives on Adversarial Classification

  • David Rios Insua,
  • Roi Naveiro and
  • Victor Gallego

5 November 2020

Adversarial classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). So far, most approaches to AC have followed a classical game-theoretic framework. This requires unrealistic common kno...

(This article belongs to the Special Issue Mathematical Models in Security, Defense, Cyber Security and Cyber Defense)
  • Article
  • Open Access
23 Citations
10,132 Views
29 Pages

Adversarial Patch Attacks on Deep-Learning-Based Face Recognition Systems Using Generative Adversarial Networks

  • Ren-Hung Hwang,
  • Jia-You Lin,
  • Sun-Ying Hsieh,
  • Hsuan-Yu Lin and
  • Chia-Liang Lin

11 January 2023

Deep learning technology has developed rapidly in recent years and has been successfully applied in many fields, including face recognition. Face recognition is used in many scenarios nowadays, including security control systems, access control manag...

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Sensors and Applications)
  • Article
  • Open Access
19 Citations
4,465 Views
15 Pages

6 March 2021

This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrus...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
4 Citations
3,951 Views
23 Pages

20 March 2023

Deep neural networks (DNNs) have been known to be vulnerable to adversarial attacks. Adversarial training (AT) is, so far, the only method that can guarantee the robustness of DNNs to adversarial attacks. However, the robustness generalization accura...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
5 Citations
3,668 Views
15 Pages

ADSAttack: An Adversarial Attack Algorithm via Searching Adversarial Distribution in Latent Space

  • Haobo Wang,
  • Chenxi Zhu,
  • Yangjie Cao,
  • Yan Zhuang and ,
  • Jie Li and
  • Xianfu Chen
  • + 1 author+ 0 author

Deep neural networks are susceptible to interference from deliberately crafted noise, which can lead to incorrect classification results. Existing approaches make less use of latent space information and conduct pixel-domain modification in the input...

(This article belongs to the Special Issue Advanced Techniques in Computing and Security)
  • Feature Paper
  • Article
  • Open Access
117 Citations
20,193 Views
19 Pages

Adversarial Attack and Defense: A Survey

  • Hongshuo Liang,
  • Erlu He,
  • Yangyang Zhao,
  • Zhe Jia and
  • Hao Li

In recent years, artificial intelligence technology represented by deep learning has achieved remarkable results in image recognition, semantic analysis, natural language processing and other fields. In particular, deep neural networks have been wide...

(This article belongs to the Special Issue Edge Computing for Urban Internet of Things)
  • Article
  • Open Access
4 Citations
3,571 Views
16 Pages

19 March 2024

Recent studies on watermarking techniques based on image carriers have demonstrated new approaches that combine adversarial perturbations against steganalysis with embedding distortions. However, while these methods successfully counter convolutional...

(This article belongs to the Topic Computational Complex Networks)
  • Article
  • Open Access
2 Citations
1,587 Views
19 Pages

Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples

  • Tasuku Nakajima,
  • Keisuke Maeda,
  • Ren Togo,
  • Takahiro Ogawa and
  • Miki Haseyama

25 April 2025

Adversarial attacks on large-scale vision–language foundation models, such as the contrastive language–image pretraining (CLIP) model, can significantly degrade performance across various tasks by generating adversarial examples that are...

(This article belongs to the Section Biomedical Sensors)
  • Article
  • Open Access
1 Citations
1,492 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
3 Citations
3,583 Views
14 Pages

A Mask-Based Adversarial Defense Scheme

  • Weizhen Xu,
  • Chenyi Zhang,
  • Fangzhen Zhao and
  • Liangda Fang

6 December 2022

Adversarial attacks hamper the functionality and accuracy of deep neural networks (DNNs) by meddling with subtle perturbations to their inputs. In this work, we propose a new mask-based adversarial defense scheme (MAD) for DNNs to mitigate the negati...

(This article belongs to the Topic Advances in Artificial Neural Networks)
  • Article
  • Open Access
14 Citations
4,052 Views
27 Pages

9 March 2025

Steganography has been widely used in the field of image privacy protection. However, with the advancement of steganalysis techniques, deep learning-based models are now capable of accurately detecting modifications in stego-images, posing a signific...

(This article belongs to the Section Multidisciplinary Applications)
  • Review
  • Open Access
147 Citations
28,999 Views
27 Pages

Adversarial Training Methods for Deep Learning: A Systematic Review

  • Weimin Zhao,
  • Sanaa Alwidian and
  • Qusay H. Mahmoud

12 August 2022

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the...

  • Article
  • Open Access
3 Citations
2,505 Views
21 Pages

5 November 2024

Adaptive adversarial attacks, where adversaries tailor their strategies with full knowledge of defense mechanisms, pose significant challenges to the robustness of adversarial detectors. In this paper, we introduce RADAR (Robust Adversarial Detection...

(This article belongs to the Special Issue Data Mining and Machine Learning in the Era of Big Knowledge and Large Models)
  • Article
  • Open Access
25 Citations
6,503 Views
18 Pages

Detection of Adversarial DDoS Attacks Using Generative Adversarial Networks with Dual Discriminators

  • Chin-Shiuh Shieh,
  • Thanh-Tuan Nguyen,
  • Wan-Wei Lin,
  • Yong-Lin Huang and ,
  • Mong-Fong Horng,
  • Tsair-Fwu Lee and
  • Denis Miu
  • + 2 authors+ 0 author

4 January 2022

DDoS (Distributed Denial of Service) has emerged as a serious and challenging threat to computer networks and information systems’ security and integrity. Before any remedial measures can be implemented, DDoS assaults must first be detected. DD...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
16 Citations
3,927 Views
16 Pages

Detection of Adversarial DDoS Attacks Using Symmetric Defense Generative Adversarial Networks

  • Chin-Shiuh Shieh,
  • Thanh-Tuan Nguyen,
  • Wan-Wei Lin,
  • Wei Kuang Lai and ,
  • Mong-Fong Horng and
  • Denis Miu
  • + 1 author+ 0 author

DDoS (distributed denial of service) attacks consist of a large number of compromised computer systems that launch joint attacks at a targeted victim, such as a server, website, or other network equipment, simultaneously. DDoS has become a widespread...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
29 Citations
4,298 Views
15 Pages

17 November 2022

Researchers are focusing on the vulnerabilities of deep learning models for remote sensing; various attack methods have been proposed, including universal adversarial examples. Existing universal adversarial examples, however, are only designed to fo...

(This article belongs to the Special Issue Adversarial Attacks and Defenses for Remote Sensing Data)
  • Article
  • Open Access
17 Citations
4,408 Views
13 Pages

7 May 2021

One of the most intriguing phenomenons related to deep learning is the so-called adversarial examples. These samples are visually equivalent to normal inputs, undetectable for humans, yet they cause the networks to output wrong results. The phenomeno...

  • Article
  • Open Access
4 Citations
4,818 Views
37 Pages

Neural-network-based models have made considerable progress in many computer vision areas over recent years. However, many works have exposed their vulnerability to malicious input data manipulation—that is, to adversarial attacks. Although man...

  • Article
  • Open Access
8 Citations
4,799 Views
18 Pages

Surreptitious Adversarial Examples through Functioning QR Code

  • Aran Chindaudom,
  • Prarinya Siritanawan,
  • Karin Sumongkayothin and
  • Kazunori Kotani

The continuous advances in the technology of Convolutional Neural Network (CNN) and Deep Learning have been applied to facilitate various tasks of human life. However, security risks of the users’ information and privacy have been increasing ra...

(This article belongs to the Special Issue Intelligent Media Processing)
  • Article
  • Open Access
115 Citations
12,009 Views
35 Pages

Context-Aware Generative Adversarial Privacy

  • Chong Huang,
  • Peter Kairouz,
  • Xiao Chen,
  • Lalitha Sankar and
  • Ram Rajagopal

1 December 2017

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but o...

(This article belongs to the Special Issue Information Theory in Machine Learning and Data Science)
  • Article
  • Open Access
1 Citations
3,951 Views
11 Pages

15 October 2023

Despite the impressive performance of deep neural networks on many different vision tasks, they have been known to be vulnerable to intentionally added noise to input images. To combat these adversarial examples (AEs), improving the adversarial robus...

(This article belongs to the Topic Adversarial Machine Learning: Theories and Applications)
  • Article
  • Open Access
1 Citations
776 Views
17 Pages

9 March 2026

Neural network models are highly susceptible to adversarial sample attacks, causing significant differences in model predictions with even minor perturbations to the samples. Adversarial training is a kind of effective technique for resisting sample...

  • Article
  • Open Access
5 Citations
3,405 Views
19 Pages

16 November 2024

Deep neural networks (DNNs) have achieved great success in various computer vision tasks. However, they are susceptible to artificially designed adversarial perturbations, which limit their deployment in security-critical applications. In this paper,...

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition (Second Edition))
  • Article
  • Open Access
4 Citations
3,280 Views
18 Pages

Clustering Approach for Detecting Multiple Types of Adversarial Examples

  • Seok-Hwan Choi,
  • Tae-u Bahk,
  • Sungyong Ahn and
  • Yoon-Ho Choi

18 May 2022

With intentional feature perturbations to a deep learning model, the adversary generates an adversarial example to deceive the deep learning model. As an adversarial example has recently been considered in the most severe problem of deep learning tec...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
8 Citations
5,506 Views
23 Pages

Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training

  • Anna Chistyakova,
  • Anastasia Antsiferova,
  • Maksim Khrebtov,
  • Sergey Lavrushkin and ,
  • Konstantin Arkhipenko,
  • Dmitriy Vatolin and
  • Denis Turdakov
  • + 2 authors+ 0 author

The adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-d...

  • Article
  • Open Access
18 Citations
6,590 Views
14 Pages

26 December 2018

Neural networks are very vulnerable to adversarial examples, which threaten their application in security systems, such as face recognition, and autopilot. In response to this problem, we propose a new defensive strategy. In our strategy, we propose...

  • Article
  • Open Access
7 Citations
3,982 Views
15 Pages

A Hybrid Adversarial Attack for Different Application Scenarios

  • Xiaohu Du,
  • Jie Yu,
  • Zibo Yi,
  • Shasha Li and ,
  • Jun Ma,
  • Yusong Tan and
  • Qinbo Wu
  • + 2 authors+ 0 author

21 May 2020

Adversarial attack against natural language has been a hot topic in the field of artificial intelligence security in recent years. It is mainly to study the methods and implementation of generating adversarial examples. The purpose is to better deal...

(This article belongs to the Special Issue Natural Language Processing: Emerging Neural Approaches and Applications)
  • Article
  • Open Access
2 Citations
2,318 Views
13 Pages

A3GT: An Adaptive Asynchronous Generalized Adversarial Training Method

  • Zeyi He,
  • Wanyi Liu,
  • Zheng Huang,
  • Yitian Chen and
  • Shigeng Zhang

15 October 2024

Adversarial attack methods can significantly improve the classification accuracy of deep learning models, but research has found that although most deep learning models with defense methods still show good classification accuracy in the face of vario...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
3 Citations
3,486 Views
26 Pages

Minimum Adversarial Examples

  • Zhenyu Du,
  • Fangzheng Liu and
  • Xuehu Yan

12 March 2022

Deep neural networks in the area of information security are facing a severe threat from adversarial examples (AEs). Existing methods of AE generation use two optimization models: (1) taking the successful attack as the objective function and limitin...

(This article belongs to the Special Issue Information Theory and Its Applications in Multimedia Security and Processing)
  • Article
  • Open Access
17 Citations
10,721 Views
26 Pages

Polymorphic Adversarial Cyberattacks Using WGAN

  • Ravi Chauhan,
  • Ulya Sabeel,
  • Alireza Izaddoost and
  • Shahram Shah Heydari

12 December 2021

Intrusion Detection Systems (IDS) are essential components in preventing malicious traffic from penetrating networks and systems. Recently, these systems have been enhancing their detection ability using machine learning algorithms. This development...

(This article belongs to the Collection Intelligent Security and Privacy Approaches against Cyber Threats)
  • Article
  • Open Access
1 Citations
2,242 Views
15 Pages

Fast-M Adversarial Training Algorithm for Deep Neural Networks

  • Yu Ma,
  • Dou An,
  • Zhixiang Gu,
  • Jie Lin and
  • Weiyu Liu

27 May 2024

Although deep neural networks have been successfully applied in many fields, research studies show that neural network models are easily disrupted by small malicious inputs, greatly reducing their performance. Such disruptions are known as adversaria...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Review
  • Open Access
2 Citations
3,592 Views
25 Pages

Advances in Brain-Inspired Deep Neural Networks for Adversarial Defense

  • Ruyi Li,
  • Ming Ke,
  • Zhanguo Dong,
  • Lubin Wang and ,
  • Tielin Zhang,
  • Minghua Du and
  • Gang Wang
  • + 2 authors+ 0 author

Deep convolutional neural networks (DCNNs) have achieved impressive performance in image recognition, object detection, etc. Nevertheless, they are susceptible to adversarial attacks and interferential noise. Adversarial attacks can mislead DCNN mode...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
22 Citations
5,058 Views
17 Pages

Random Untargeted Adversarial Example on Deep Neural Network

  • Hyun Kwon,
  • Yongchul Kim,
  • Hyunsoo Yoon and
  • Daeseon Choi

10 December 2018

Deep neural networks (DNNs) have demonstrated remarkable performance in machine learning areas such as image recognition, speech recognition, intrusion detection, and pattern analysis. However, it has been revealed that DNNs have weaknesses in the fa...

  • Article
  • Open Access
1,289 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...

  • Review
  • Open Access
392 Citations
39,439 Views
29 Pages

4 March 2019

In recent years, artificial intelligence technologies have been widely used in computer vision, natural language processing, automatic driving, and other fields. However, artificial intelligence systems are vulnerable to adversarial attacks, which li...

(This article belongs to the Special Issue Advances in Deep Learning)
  • Feature Paper
  • Article
  • Open Access
27 Citations
4,482 Views
13 Pages

Adversarial examples are theorized to exist for every type of neural network application. Adversarial examples have been proven to exist in neural networks for visual-spectrum applications and that they are highly transferable between such neural net...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
2,449 Views
12 Pages

Stylized Pairing for Robust Adversarial Defense

  • Dejian Guan,
  • Wentao Zhao and
  • Xiao Liu

18 September 2022

Recent studies show that deep neural networks (DNNs)-based object recognition algorithms overly rely on object textures rather than global object shapes, and DNNs are also vulnerable to human-less perceptible adversarial perturbations. Based on these...

(This article belongs to the Special Issue Machine Learning for Network Security)
  • Article
  • Open Access
5 Citations
2,425 Views
24 Pages

To improve the robustness of intrusion detection systems constructed using deep learning models, a method based on an auxiliary adversarial training WGAN (AuxAtWGAN) is proposed from the defender’s perspective. First, one-dimensional traffic da...

  • Article
  • Open Access
13 Citations
5,508 Views
24 Pages

Evaluation of GAN-Based Model for Adversarial Training

  • Weimin Zhao,
  • Qusay H. Mahmoud and
  • Sanaa Alwidian

1 March 2023

Deep learning has been successfully utilized in many applications, but it is vulnerable to adversarial samples. To address this vulnerability, a generative adversarial network (GAN) has been used to train a robust classifier. This paper presents a no...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
3 Citations
3,258 Views
16 Pages

4 September 2024

Adversarial training is one of the most successful approaches to improve model robustness against maliciously crafted data. Instead of training on a clean dataset, the model is trained on adversarial data generated on the fly. Based on that, a group...

of 130