Skip to Content

654 Results Found

  • Article
  • Open Access
5 Citations
4,713 Views
19 Pages

ShrewdAttack: Low Cost High Accuracy Model Extraction

  • Yang Liu,
  • Ji Luo,
  • Yi Yang,
  • Xuan Wang and ,
  • Mehdi Gheisari and
  • Feng Luo
  • + 1 author+ 0 author

2 February 2023

Machine learning as a service (MLaaS) plays an essential role in the current ecosystem. Enterprises do not need to train models by themselves separately. Instead, they can use well-trained models provided by MLaaS to support business activities. Howe...

(This article belongs to the Special Issue Trustworthy AI: Information Theoretic Perspectives)
  • Article
  • Open Access
5 Citations
5,263 Views
22 Pages

29 April 2024

In the rapidly evolving landscape of cybersecurity, model extraction attacks pose a significant challenge, undermining the integrity of machine learning models by enabling adversaries to replicate proprietary algorithms without direct access. This pa...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
394 Views
34 Pages

Security Evaluation of Classical Machine Learning Models Under Poisoning, Evasion, and Model Extraction Attacks

  • Hannelore Sebestyen,
  • Elisa Valentina Moisi,
  • Simina Maria Coman and
  • Daniela Elena Popescu

8 September 2026

Classical machine learning (ML) models, including Logistic Regression (LR), Support Vector Machines (SVM), Random Forests (RF), and XGBoost, remain widely used in practical applications because of their efficiency, interpretability, and relatively lo...

  • Article
  • Open Access
5 Citations
7,894 Views
19 Pages

Targeted Training Data Extraction—Neighborhood Comparison-Based Membership Inference Attacks in Large Language Models

  • Huan Xu,
  • Zhanhao Zhang,
  • Xiaodong Yu,
  • Yingbo Wu and ,
  • Zhiyong Zha,
  • Bo Xu,
  • Wenfeng Xu,
  • Menglan Hu and
  • Kai Peng
  • + 4 authors+ 0 author

14 August 2024

A large language model refers to a deep learning model characterized by extensive parameters and pretraining on a large-scale corpus, utilized for processing natural language text and generating high-quality text output. The increasing deployment of...

(This article belongs to the Special Issue Security and Privacy in Machine Learning and Artificial Intelligence (AI))
  • Article
  • Open Access
6 Citations
2,115 Views
17 Pages

9 October 2025

The secondary use of electronic health records is essential for developing artificial intelligence-based clinical decision support systems. However, even after direct identifiers are removed, de-identified electronic health records remain vulnerable...

(This article belongs to the Special Issue Digital Innovations in Healthcare)
  • Article
  • Open Access
380 Views
20 Pages

Hybrid Watermarking and Adaptive Misinformation for Protection Against AI Model Extraction in Edge-Deployed Cyber-Physical Security

  • Fatimah Azzahrah binti Razali,
  • Mohamed Hadi Habaebi and
  • Mohammed Abdullah Salem Al-Hussaini

8 September 2026

Artificial intelligence (AI) models are increasingly deployed in edge-deployed cyber-physical security systems for tasks encompassing monitoring, threat classification, and automated decision-making. While these models offer robust performance, their...

  • Article
  • Open Access
4 Citations
3,608 Views
21 Pages

29 August 2024

Cybercriminals have become an imperative threat because they target the most valuable resource on earth, data. Organizations prepare against cyber attacks by creating Cyber Security Incident Response Teams (CSIRTs) that use various technologies to mo...

(This article belongs to the Special Issue Advanced IoT Systems in Smart Cities: 2nd Edition)
  • Article
  • Open Access
1,067 Views
33 Pages

Enhancing Data Privacy in Large Language Models Through Private Association Editing

  • Davide Venditti,
  • Elena Sofia Ruzzetti,
  • Giancarlo A. Xompero,
  • Cristina Giannone and ,
  • Andrea Favalli,
  • Raniero Romagnoli and
  • Fabio Massimo Zanzotto
  • + 2 authors+ 0 author

Large language models (LLMs) require a significant redesign in solutions to preserve privacy in data-intensive applications due to their text-generation capabilities. Indeed, LLMs tend to memorize and emit private information when maliciously prompte...

(This article belongs to the Section Privacy)
  • Article
  • Open Access
6 Citations
2,969 Views
32 Pages

Extracting Optimal Number of Features for Machine Learning Models in Multilayer IoT Attacks

  • Badeea Al Sukhni,
  • Soumya K. Manna,
  • Jugal M. Dave and
  • Leishi Zhang

19 December 2024

The rapid integration of Internet of Things (IoT) systems in various sectors has escalated security risks due to sophisticated multilayer attacks that compromise multiple security layers and lead to significant data loss, personal information theft,...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
37 Citations
4,438 Views
15 Pages

Advanced Persistent Threat (APT) seriously threatens a nation’s cyberspace security. Current defense technologies are typically unable to detect it effectively since APT attack is complex and the signatures for detection are not clear. To enhan...

(This article belongs to the Special Issue AI-Driven Network Security and Privacy)
  • Article
  • Open Access
14 Citations
9,155 Views
19 Pages

Data Stealing Attacks against Large Language Models via Backdooring

  • Jiaming He,
  • Guanyu Hou,
  • Xinyue Jia,
  • Yangyang Chen and ,
  • Wenqi Liao,
  • Yinhang Zhou and
  • Rang Zhou
  • + 2 authors+ 0 author

Large language models (LLMs) have gained immense attention and are being increasingly applied in various domains. However, this technological leap forward poses serious security and privacy concerns. This paper explores a novel approach to data steal...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
18 Citations
5,967 Views
17 Pages

Deep-Learning Based Injection Attacks Detection Method for HTTP

  • Chunhui Zhao,
  • Shuaijie Si,
  • Tengfei Tu,
  • Yijie Shi and
  • Sujuan Qin

13 August 2022

In the context of the new era of high digitization and informatization, the emergence of the internet and artificial intelligence technologies has profoundly changed people’s lifestyles. The traditional cyber attack detection has become increas...

(This article belongs to the Special Issue Artificial Intelligence and Natural Computing: Theory, Methodology and Applications)
  • 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
8 Citations
2,181 Views
21 Pages

Detection of Cyber-Attacks in a Discrete Event System Based on Deep Learning

  • Sichen Ding,
  • Gaiyun Liu,
  • Li Yin,
  • Jianzhou Wang and
  • Zhiwu Li

25 August 2024

This paper addresses the problem of cyber-attack detection in a discrete event system by proposing a novel model. The model utilizes graph convolutional networks to extract spatial features from event sequences. Subsequently, it employs gated recurre...

(This article belongs to the Special Issue Discrete Event Dynamic Systems and Applications)
  • Article
  • Open Access
31 Citations
7,042 Views
26 Pages

16 September 2023

Due to the severe imbalance in the quantities of normal samples and attack samples, as well as among different types of attack samples, intrusion detection systems suffer from low detection rates for rare-class attack data. In this paper, we propose...

(This article belongs to the Special Issue Network Intrusion Detection Using Deep Learning)
  • Article
  • Open Access
1,082 Views
34 Pages

18 November 2025

Graph-based Recommender Systems (GRSs) model complex user–item relationships. They offer improved accuracy and personalization in recommendations compared to traditional models. However, GRSs also face severe challenges from novel poisoning att...

  • Article
  • Open Access
13 Citations
4,000 Views
17 Pages

2 November 2023

Planned and targeted attacks, such as the advanced persistent threat (APT), are highly sophisticated forms of attack. They involve numerous steps and are intended to remain within a system for an extended length of period before progressing to the ne...

(This article belongs to the Special Issue Advanced Machine Learning Applications for Security, Privacy, and Reliability)
  • Article
  • Open Access
3 Citations
4,674 Views
25 Pages

Evaluating and Enhancing the Robustness of Sustainable Neural Relationship Classifiers Using Query-Efficient Black-Box Adversarial Attacks

  • Ijaz Ul Haq,
  • Zahid Younas Khan,
  • Arshad Ahmad,
  • Bashir Hayat and ,
  • Asif Khan,
  • Ye-Eun Lee and
  • Ki-Il Kim
  • + 2 authors+ 0 author

24 May 2021

Neural relation extraction (NRE) models are the backbone of various machine learning tasks, including knowledge base enrichment, information extraction, and document summarization. Despite the vast popularity of these models, their vulnerabilities re...

(This article belongs to the Special Issue Sustainable Growth in Engineering and Technology Management)
  • Article
  • Open Access
17 Citations
3,253 Views
20 Pages

Marine sensors are highly vulnerable to illegal access network attacks. Moreover, the nation’s meteorological and hydrological information is at ever-increasing risk, which calls for a prompt and in depth analysis of the network behavior and tr...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
35 Citations
7,584 Views
30 Pages

An Explanation of the LSTM Model Used for DDoS Attacks Classification

  • Abdulmuneem Bashaiwth,
  • Hamad Binsalleeh and
  • Basil AsSadhan

31 July 2023

With the rise of DDoS attacks, several machine learning-based attack detection models have been used to mitigate malicious behavioral attacks. Understanding how machine learning models work is not trivial. This is particularly true for complex and no...

  • Article
  • Open Access
6 Citations
4,240 Views
25 Pages

17 June 2023

The outstanding performance of deep neural networks (DNNs) in multiple computer vision in recent years has promoted its widespread use in aerial image semantic segmentation. Nonetheless, prior research has demonstrated the high susceptibility of DNNs...

(This article belongs to the Special Issue Adversarial Attacks and Defenses for Remote Sensing Data)
  • Article
  • Open Access
44 Citations
8,194 Views
15 Pages

Phishing attacks are a major threat to online security, resulting in millions of dollars in losses. These attacks constantly evolve, forcing the cyber security community to improve detection systems. One major problem with current detection systems i...

(This article belongs to the Special Issue Advancements in Cross-Disciplinary AI: Theory and Application—2nd Edition)
  • Article
  • Open Access
5 Citations
11,515 Views
26 Pages

Terrorism perpetrated in any country by either internal or external actors jeopardizes the country’s security, economic growth, societal peace, and harmony. Hence, accurate modelling of terrorism has become a necessary component of the national...

  • Article
  • Open Access
24 Citations
3,960 Views
17 Pages

Efficient Multi-Source Self-Attention Data Fusion for FDIA Detection in Smart Grid

  • Yi Wu,
  • Qiankuan Wang,
  • Naiwang Guo,
  • Yingjie Tian and ,
  • Fengyong Li and
  • Xiangjing Su
  • + 1 author+ 0 author

4 May 2023

As a new cyber-attack method in power cyber physical systems, false-data-injection attacks (FDIAs) mainly disturb the operating state of power systems by tampering with the measurement data of sensors, thereby avoiding bad-data detection by the power...

(This article belongs to the Special Issue Security, Communication and Privacy in Internet of Things: Symmetry and Advances)
  • Article
  • Open Access
1,044 Views
24 Pages

Deep neural networks (DNNs) represent critical intellectual property that model owners urgently need to protect. With the increasing value of models, malicious attackers increasingly attempt to extract model functionality through techniques such as f...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
2 Citations
5,703 Views
18 Pages

In recent years, various Remote Code Execution vulnerabilities on the Internet have been exposed frequently; thus, more and more security researchers have begun to pay attention to the detection of Remote Code Execution attacks. In this paper, we foc...

(This article belongs to the Section Cybersecurity)
  • Article
  • Open Access
1,609 Views
22 Pages

Correlation Analysis of APT Attack Organizations Based on Knowledge Graphs

  • Haohui Su,
  • Xuan Zhang,
  • Lincheng Li and
  • Lvjun Zheng

Advanced Persistent Threats (APTs) exhibit covert behaviors, long attack cycles, and fragmented intelligence, creating challenges for correlation analysis and attribution. This work proposes a unified knowledge-graph-based framework for multi-level A...

(This article belongs to the Special Issue Enhancing Cybersecurity: Advanced Attack Detection and Defense Techniques)
  • Article
  • Open Access
7 Citations
3,393 Views
17 Pages

6 March 2023

The adversarial attack is crucial to improving the robustness of deep learning models; they help improve the interpretability of deep learning and also increase the security of the models in real-world applications. However, existing attack algorithm...

(This article belongs to the Special Issue Selected Feature Papers from China Information Theory Conference (CIT) & the Annual Conference on Information Theory of the Chinese Institute of Electronics (CIEIT))
  • Article
  • Open Access
2 Citations
3,109 Views
13 Pages

12 January 2024

In detecting large-scale attacks, deep neural networks (DNNs) are an effective approach based on high-quality training data samples. Feature selection and feature extraction are the primary approaches for data quality enhancement for high-accuracy in...

(This article belongs to the Special Issue Information and Future Internet Security, Trust and Privacy II)
  • Article
  • Open Access
9 Citations
2,559 Views
15 Pages

SDN is a modern internet architecture that has transformed the traditional internet structure in recent years. By segregating the control and data planes of the network, SDN facilitates centralized management, scalability, dynamism, and programmabili...

  • Article
  • Open Access
24 Citations
3,994 Views
23 Pages

Blind Watermarking of Color Medical Images Using Hadamard Transform and Fractional-Order Moments

  • Mostafa M. Abdel-Aziz,
  • Khalid M. Hosny,
  • Nabil A. Lashin and
  • Mostafa M. Fouda

25 November 2021

This paper proposes a new blind, color image watermarking method using fast Walsh–Hadamard transformation (FWHT) and multi-channel fractional Legendre–Fourier moments (MFrLFMs). The input host color image is first split into 4 × 4 n...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
10 Citations
2,819 Views
16 Pages

1 December 2022

Owing to their wide application, Internet of Things systems have been the target of malicious attacks. These attacks included DoS, flood, SlowITe, malformed, and brute-force attacks. A dataset that includes these attacks was recently released. Howeve...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
2 Citations
972 Views
29 Pages

1 November 2025

The deployment of deep learning models in Internet of Things (IoT) systems is increasingly threatened by adversarial attacks. To address the challenge of effectively detecting adversarial examples generated by Generative Adversarial Networks (AdvGANs...

(This article belongs to the Special Issue IoT Network Security (Second Edition))
  • Article
  • Open Access
2 Citations
1,831 Views
31 Pages

Symmetric Dual-Phase Framework for APT Attack Detection Based on Multi-Feature-Conditioned GAN and Graph Convolutional Network

  • Qi Liu,
  • Yao Dong,
  • Chao Zheng,
  • Hualin Dai and ,
  • Jiaxing Wang,
  • Liyuan Ning and
  • Qiqi Liang
  • + 2 authors+ 0 author

30 June 2025

Advanced persistent threat (APT) attacks present significant challenges to cybersecurity due to their covert nature, high complexity, and ability to operate across multiple temporal and spatial scales. Existing detection techniques often struggle wit...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
15 Citations
6,531 Views
10 Pages

2 January 2022

Fault attacks are traditionally considered under a threat model that assumes the device under test is in the possession of the attacker. We propose a variation on this model. In our model, the attacker integrates a fault injection circuit into a mali...

(This article belongs to the Special Issue Side Channel Attacks in Embedded Systems)
  • Article
  • Open Access
10 Citations
4,446 Views
17 Pages

6 August 2024

As the informatization of power systems advances, the secure operation of power systems faces various potential network attacks and threats. The false data injection attack (FDIA) is a common attack mode that can lead to abnormal system operations an...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
552 Views
31 Pages

Cloud computing is one of the essential computing platforms for modern enterprises. About 98 percent of large businesses will use cloud computing services in 2025 to enable remote working. The highly distributed structures of cloud computing are pron...

(This article belongs to the Special Issue Artificial Intelligence/Machine Learning (AI/ML)-Based Tools for Cyber Security)
  • Article
  • Open Access
13 Citations
5,215 Views
29 Pages

Intrusion Detection System Based on Multi-Level Feature Extraction and Inductive Network

  • Junyi Mao,
  • Xiaoyu Yang,
  • Bo Hu,
  • Yizhen Lu and
  • Guangqiang Yin

With the rapid development of the internet, network security threats are becoming increasingly complex and diverse, making traditional intrusion detection systems (IDSs) inadequate for handling the growing variety of sophisticated attacks. In particu...

(This article belongs to the Special Issue Artificial Intelligence in Cyberspace Security)
  • Article
  • Open Access
7 Citations
4,625 Views
20 Pages

Risk Measurement Method for Privilege Escalation Attacks on Android Apps Based on Process Algebra

  • Limin Shen,
  • Hui Li,
  • Hongyi Wang,
  • Yihuan Wang and ,
  • Jiayin Feng and
  • Yuqing Jian
  • + 1 author+ 0 author

On the Android platform, information leakage can use an application-layer privilege escalation attack composed of multi-app collusion. However, the detection effect of a single app that can construct privilege escalation attacks is not good. Furtherm...

(This article belongs to the Special Issue Cyberspace Security, Privacy & Forensics)
  • Article
  • Open Access
7 Citations
3,071 Views
18 Pages

22 November 2022

For attack detection in the smart grid, transfer learning is a promising solution to tackle data distribution divergence and maintain performance when facing system and attack variations. However, there are still two challenges when introducing trans...

(This article belongs to the Special Issue Volume II: Situation Awareness for Smart Distribution Systems)
  • Article
  • Open Access
171 Citations
14,450 Views
15 Pages

SCADA System Testbed for Cybersecurity Research Using Machine Learning Approach

  • Marcio Andrey Teixeira,
  • Tara Salman,
  • Maede Zolanvari,
  • Raj Jain and ,
  • Nader Meskin and
  • Mohammed Samaka
  • + 1 author+ 0 author

This paper presents the development of a Supervisory Control and Data Acquisition (SCADA) system testbed used for cybersecurity research. The testbed consists of a water storage tank’s control system, which is a stage in the process of water treatmen...

  • Article
  • Open Access
2 Citations
2,730 Views
14 Pages

18 August 2022

The transferability of adversarial examples allows the attacker to fool deep neural networks (DNNs) without knowing any information about the target models. The current input transformation-based method generates adversarial examples by transforming...

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)
  • 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
6 Citations
2,953 Views
16 Pages

Multi-Dimensional Fusion Deep Learning for Side Channel Analysis

  • Tuo Deng,
  • Huanyu Wang,
  • Dalin He,
  • Naixue Xiong and ,
  • Wei Liang and
  • Junnian Wang
  • + 1 author+ 0 author

22 November 2023

The rapid advancement of deep learning has significantly heightened the threats posed by Side-Channel Attacks (SCAs) to information security, transforming their effectiveness to a degree several orders of magnitude superior to conventional signal pro...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
590 Views
20 Pages

Network technology has advanced rapidly in recent years, and distributed denial-of-service (DDoS) attacks have grown more diverse, stealthy, and large-scale. Traditional detection approaches struggle to process long network traffic sequences and loca...

(This article belongs to the Special Issue New Technologies for Cybersecurity)
  • Article
  • Open Access
9 Citations
6,908 Views
17 Pages

22 April 2025

Given the significant risk that heart disease, particularly heart attacks, poses to individuals’ lives, it is crucial to develop effective techniques for early detection. Advanced machine learning and deep learning algorithms have the ability t...

(This article belongs to the Special Issue Learning and Knowledge: Theoretical Issues and Applications)
  • Article
  • Open Access
20 Citations
7,987 Views
22 Pages

As the Industrial Internet of Things (IIoT) increasingly integrates with traditional networks, advanced persistent threats (APTs) pose significant risks to critical infrastructure. Traditional Intrusion Detection Systems (IDSs) and Anomaly Detection...

(This article belongs to the Special Issue AI-Based Solutions for Cybersecurity)
  • Article
  • Open Access
5 Citations
4,428 Views
17 Pages

Utilising Flow Aggregation to Classify Benign Imitating Attacks

  • Hanan Hindy,
  • Robert Atkinson,
  • Christos Tachtatzis,
  • Ethan Bayne and ,
  • Miroslav Bures and
  • Xavier Bellekens
  • + 1 author+ 0 author

4 March 2021

Cyber-attacks continue to grow, both in terms of volume and sophistication. This is aided by an increase in available computational power, expanding attack surfaces, and advancements in the human understanding of how to make attacks undetectable. Uns...

(This article belongs to the Special Issue Security and Privacy in the Internet of Things (IoT))
  • Article
  • Open Access
65 Citations
15,119 Views
21 Pages

Deep Autoencoder-Based Integrated Model for Anomaly Detection and Efficient Feature Extraction in IoT Networks

  • Khaled A. Alaghbari,
  • Heng-Siong Lim,
  • Mohamad Hanif Md Saad and
  • Yik Seng Yong

25 August 2023

The intrusion detection system (IDS) is a promising technology for ensuring security against cyber-attacks in internet-of-things networks. In conventional IDS, anomaly detection and feature extraction are performed by two different models. In this pa...

  • Article
  • Open Access
10 Citations
6,198 Views
45 Pages

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

  • Majed Altoub,
  • Fahad AlQurashi,
  • Tan Yigitcanlar,
  • Juan M. Corchado and
  • Rashid Mehmood

31 October 2022

Deep neural networks (DNNs) have successfully delivered cutting-edge performance in several fields. With the broader deployment of DNN models on critical applications, the security of DNNs has become an active and yet nascent area. Attacks against DN...

(This article belongs to the Section Computing and Artificial Intelligence)

of 14