Skip to Content

510 Results Found

  • Article
  • Open Access
4 Citations
5,227 Views
25 Pages

14 December 2022

Recent efforts have shown that training data is not secured through the generalization and abstraction of algorithms. This vulnerability to the training data has been expressed through membership inference attacks that seek to discover the use of spe...

(This article belongs to the Section Security Engineering & Applications)
  • Article
  • Open Access
9 Citations
7,087 Views
26 Pages

Comparative Analysis of Membership Inference Attacks in Federated and Centralized Learning

  • Ali Abbasi Tadi,
  • Saroj Dayal,
  • Dima Alhadidi and
  • Noman Mohammed

19 November 2023

The vulnerability of machine learning models to membership inference attacks, which aim to determine whether a specific record belongs to the training dataset, is explored in this paper. Federated learning allows multiple parties to independently tra...

(This article belongs to the Special Issue Best IDEAS: International Database Engineered Applications Symposium)
  • Article
  • Open Access
3 Citations
2,511 Views
12 Pages

Threshold Filtering for Detecting Label Inference Attacks in Vertical Federated Learning

  • Liansheng Ding,
  • Haibin Bao,
  • Qingzhe Lv,
  • Feng Zhang and ,
  • Zhouyang Zhang,
  • Jianliang Han and
  • Shuang Ding
  • + 2 authors+ 0 author

8 November 2024

Federated learning, as an emerging machine-learning method, has received widespread attention because it allows users to train locally during the training process and uses relevant cryptographic knowledge to safeguard the privacy of data during model...

(This article belongs to the Section Networks)
  • Article
  • Open Access
9 Citations
4,754 Views
15 Pages

7 September 2023

Machine learning deployment on edge devices has faced challenges such as computational costs and privacy issues. Membership inference attack (MIA) refers to the attack where the adversary aims to infer whether a data sample belongs to the training se...

(This article belongs to the Special Issue Security of Sensor Network Systems and Circuits from a Hardware Perspective)
  • Review
  • Open Access
642 Views
24 Pages

Recent Advances and Open Challenges in Mitigating Inference-Time Attacks on Large Language Models

  • Berkay Özçam,
  • Mustafa Kara,
  • Muhammed Ali Aydın and
  • Hasan Hüseyin Balık

18 August 2026

The rapid integration of Large Language Models into high-stakes domains has elevated inference-time attacks into a primary security concern for production deployments. These attacks are adversarial techniques that exploit models exclusively through t...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
2 Citations
5,180 Views
29 Pages

User Mobility Modeling in Crowdsourcing Application to Prevent Inference Attacks

  • Farid Yessoufou,
  • Salma Sassi,
  • Elie Chicha,
  • Richard Chbeir and
  • Jules Degila

28 August 2024

With the rise of the Internet of Things (IoT), mobile crowdsourcing has become a leading application, leveraging the ubiquitous presence of smartphone users to collect and process data. Spatial crowdsourcing, which assigns tasks based on users’...

  • Article
  • Open Access
3 Citations
2,064 Views
20 Pages

1 October 2025

Graph neural networks (GNNs) are deep learning models that process structured graph data. By leveraging their graphs/node classification and link prediction capabilities, they have been effectively applied in multiple domains such as community detect...

  • Article
  • Open Access
5 Citations
7,905 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
1 Citations
8,269 Views
19 Pages

Membership Inference Attacks Fueled by Few-Shot Learning to Detect Privacy Leakage and Address Data Integrity

  • Daniel Jiménez-López,
  • Nuria Rodríguez-Barroso,
  • M. Victoria Luzón,
  • Javier Del Ser and
  • Francisco Herrera

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership inference attacks (MIAs) exploit this to obtain confidential information about the data used for training, aimi...

(This article belongs to the Section Safety, Security, Privacy, and Cyber Resilience)
  • Article
  • Open Access
236 Views
26 Pages

15 October 2026

Membership inference attacks (MIAs) determine whether a sample was used to train a target model. Existing attacks often require abundant auxiliary data or many reference models, which may be unavailable in restricted services. We propose a meta-learn...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
1 Citations
3,359 Views
15 Pages

LTU Attacker for Membership Inference

  • Joseph Pedersen,
  • Rafael Muñoz-Gómez,
  • Jiangnan Huang,
  • Haozhe Sun and ,
  • Wei-Wei Tu and
  • Isabelle Guyon
  • + 1 author+ 0 author

20 July 2022

We address the problem of defending predictive models, such as machine learning classifiers (Defender models), against membership inference attacks, in both the black-box and white-box setting, when the trainer and the trained model are publicly rele...

  • Article
  • Open Access
4 Citations
2,272 Views
23 Pages

Leveraging Multiple Adversarial Perturbation Distances for Enhanced Membership Inference Attack in Federated Learning

  • Fan Xia,
  • Yuhao Liu,
  • Bo Jin,
  • Zheng Yu and ,
  • Xingwei Cai,
  • Hao Li,
  • Zhiyong Zha,
  • Dai Hou and
  • Kai Peng
  • + 4 authors+ 0 author

18 December 2024

In recent years, federated learning (FL) has gained significant attention for its ability to protect data privacy during distributed training. However, it also introduces new privacy leakage risks. Membership inference attacks (MIAs), which aim to de...

(This article belongs to the Section F: Engineering and Materials)
  • Article
  • Open Access
5 Citations
1,733 Views
19 Pages

11 January 2025

Flight operations data play a central role in ensuring flight safety, optimizing operations, and driving innovation. However, these data have become a key target for cyber-attacks, and are especially vulnerable to property inference attacks. Aiming a...

(This article belongs to the Section Air Traffic and Transportation)
  • Article
  • Open Access
1 Citations
2,129 Views
16 Pages

3 May 2025

Graph neural networks (GNNs) are widely used for graph-structured data. However, GNNs are vulnerable to membership inference attacks (MIAs) in graph classification tasks, which determine whether a graph was in the training set, risking the leakage of...

  • Article
  • Open Access
16 Citations
4,677 Views
24 Pages

29 December 2022

In response to the increasing threat of hypersonic weapons, it is of great importance for the defensive side to achieve fast prediction of their feasible attack domain and online inference of their most probable targets. In this study, an online foot...

(This article belongs to the Special Issue Mathematical Problems in Aerospace)
  • Article
  • Open Access

19 November 2026

Federated learning provides a privacy-enhancing paradigm for distributed collaborative learning across diverse application scenarios, yet it inherently contains vulnerabilities that can lead to information leakage. As critical parameters in deep neur...

(This article belongs to the Special Issue Cybersecurity, Privacy, and Trust in Intelligent Networked Systems)
  • Article
  • Open Access
2 Citations
2,831 Views
16 Pages

21 January 2022

Taking advantage of precise positioning technology, location-based service (LBS) has brought a lot of convenience to people’s daily life and made the city smarter. However, the LBS applications also bring some challenges to personal location pr...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
18 Citations
5,939 Views
19 Pages

A Mamdani Type Fuzzy Inference System to Calculate Employee Susceptibility to Phishing Attacks

  • Yahya Lambat,
  • Nick Ayres,
  • Leandros Maglaras and
  • Mohamed Amine Ferrag

29 September 2021

It is a well known fact that the weakest link in a cyber secure system is the people who configure, manage or use it. Security breaches are persistently being attributed to human error. Social engineered based attacks are becoming more sophisticated...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
3 Citations
3,367 Views
26 Pages

Detecting Inference Attacks Involving Raw Sensor Data: A Case Study

  • Paul Lachat,
  • Nadia Bennani,
  • Veronika Rehn-Sonigo,
  • Lionel Brunie and
  • Harald Kosch

24 October 2022

With the advent of sensors, more and more services are developed in order to provide customers with insights about their health and their appliances’ energy consumption at home. To do so, these services use new mining algorithms that create new...

(This article belongs to the Special Issue Data and Privacy Management in Sensor Networks)
  • Article
  • Open Access
2 Citations
2,529 Views
25 Pages

Mitigating Membership Inference Attacks via Generative Denoising Mechanisms

  • Zhijie Yang,
  • Xiaolong Yan,
  • Guoguang Chen and
  • Xiaoli Tian

24 September 2025

Membership Inference Attacks (MIAs) pose a significant threat to privacy in modern machine learning systems, enabling adversaries to determine whether a specific data record was used during model training. Existing defense techniques often degrade mo...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
4 Citations
3,010 Views
14 Pages

17 February 2020

Location-based social networks have been widely used. However, due to the lack of effective and safe data management, a large number of privacy disclosures commonly occur. Thus, academia and industry have needed to focus more on location privacy prot...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
855 Views
27 Pages

16 December 2025

Historical inference attacks pose a critical privacy threat in mobile edge computing (MEC), where adversaries exploit long-term task and location patterns to infer users’ sensitive information. To address this challenge, we propose a privacy-pr...

(This article belongs to the Topic Intelligent Optimization, Decision-Making and Privacy Preservation in Cyber–Physical Systems)
  • Article
  • Open Access
408 Views
46 Pages

MobiTrust: Risk-Bounded Adaptive Split Inference Under Mobility, Privacy Leakage, and Latent-Space Attacks

  • Salam Al-E’mari,
  • Yousef Sanjalawe,
  • Muder Almiani and
  • Mohammad A. Alsharaiah

14 October 2026

Split inference lets a mobile device run the first layers of a neural network locally and hand the intermediate representation to an edge server, trading raw data disclosure for communication and offloaded computation. The common assumption that keep...

(This article belongs to the Section ICT Infrastructures for Cybersecurity)
  • Article
  • Open Access
1 Citations
982 Views
21 Pages

16 April 2026

The proliferation of Enterprise Networks, characterized by heterogeneous devices, distributed data sources, and increasingly sophisticated cyber threats, has exposed the limitations of traditional perimeter-based security models. Guided by the princi...

(This article belongs to the Special Issue Advances in Deep Learning for Complex Combinatorial Optimization: Applications in Cybersecurity, Healthcare, and Intelligent Systems)
  • Article
  • Open Access
6 Citations
2,126 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
2 Citations
1,974 Views
29 Pages

A Trajectory Prediction Method for Reentry Glide Vehicles via Adaptive Cost Function

  • Yangchao He,
  • Jiong Li,
  • Lei Shao,
  • Chijun Zhou and
  • Xiangwei Bu

16 January 2025

This paper proposes a trajectory prediction method via the adaptive cost function to address the difficulties in inferring the attack intention and maneuver mode, as well as the accumulation of prediction error during the trajectory prediction of ree...

  • Article
  • Open Access
1 Citations
2,937 Views
20 Pages

Protecting Private Information for Two Classes of Aggregated Database Queries

  • Xuechao Yang,
  • Xun Yi,
  • Andrei Kelarev,
  • Leanne Rylands and ,
  • Yuqing Lin and
  • Joe Ryan
  • + 1 author+ 0 author

An important direction of informatics is devoted to the protection of privacy of confidential information while providing answers to aggregated queries that can be used for analysis of data. Protecting privacy is especially important when aggregated...

  • Article
  • Open Access
8 Citations
4,361 Views
15 Pages

Is Homomorphic Encryption-Based Deep Learning Secure Enough?

  • Jinmyeong Shin,
  • Seok-Hwan Choi and
  • Yoon-Ho Choi

24 November 2021

As the amount of data collected and analyzed by machine learning technology increases, data that can identify individuals is also being collected in large quantities. In particular, as deep learning technology—which requires a large amount of a...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
5 Citations
1,996 Views
44 Pages

Autonomous Maneuver Decision-Making for Unmanned Combat Aerial Vehicle Based on Modified Marine Predator Algorithm and Fuzzy Inference

  • Yuequn Luo,
  • Dali Ding,
  • Mulai Tan,
  • Yidong Liu and ,
  • Ning Li,
  • Huan Zhou and
  • Fumin Wang
  • + 2 authors+ 0 author

26 March 2025

In recent years, autonomous maneuver decision-making has emerged as a key technology in autonomous air combat confrontation, garnering widespread attention. A method combining the modified marine predator algorithm (MMPA) and fuzzy inference is propo...

  • Article
  • Open Access
366 Views
43 Pages

In the industrial edge-to-cloud continuum, data is often privacy-sensitive and spans multiple organizations that do not fully trust one another, making central aggregation of raw data undesirable and often non-compliant with regulations such as the G...

(This article belongs to the Special Issue Industrial Networks of the Future Across the Edge-to-Cloud Continuum)
  • Article
  • Open Access
1 Citations
1,089 Views
28 Pages

An Agent-Based System for Location Privacy Protection in Location-Based Services

  • Omar F. Aloufi,
  • Ahmed S. Alfakeeh and
  • Fahad M. Alotaibi

Location-based services (LBSs) are a crucial element of the Internet of Things (IoT) and have garnered significant attention from both researchers and users, driven by the rise of wireless devices and a growing user base. However, the use of LBS-enab...

  • Article
  • Open Access
1,982 Views
25 Pages

Neighborhood Deviation Attack Against In-Context Learning

  • Dai Hou,
  • Zhenkai Yang,
  • Lei Zheng,
  • Bo Jin and ,
  • Huan Xu,
  • Ying Li,
  • Bo Xu and
  • Kai Peng
  • + 3 authors+ 0 author

10 April 2025

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks using only a few examples, without requiring fine-tuning. However, the new privacy and security risks brought about by this increasing capability have not received e...

(This article belongs to the Special Issue Security and Privacy in Machine Learning and Artificial Intelligence (AI))
  • Article
  • Open Access
7 Citations
3,444 Views
22 Pages

Novel Synthetic Dataset Generation Method with Privacy-Preserving for Intrusion Detection System

  • JaeCheol Kim,
  • Seungun Park,
  • Jaesik Cha,
  • Eunyeong Son and
  • Yunsik Son

30 September 2025

The expansion of Internet of Things (IoT) networks has enabled real-time data collection and automation across smart cities, healthcare, and agriculture, delivering greater convenience and efficiency; however, exposure to diverse threats has also inc...

(This article belongs to the Special Issue Advanced Technologies in Data and Information Security, Fourth Edition)
  • Review
  • Open Access
4 Citations
2,705 Views
21 Pages

Edge intelligence is an emerging paradigm generated by the deep integration of artificial intelligence (AI) and edge computing. It enables data to remain at the edge without being sent to remote cloud servers, lowering response time, saving bandwidth...

(This article belongs to the Section Networks)
  • Article
  • Open Access
988 Views
23 Pages

24 March 2026

The rapid adoption of diffusion models in medical imaging has raised significant concerns regarding data privacy, especially their susceptibility to Membership Inference Attacks (MIAs). However, the privacy risks associated with diffusion models in t...

  • Article
  • Open Access
4 Citations
2,317 Views
20 Pages

Public administration frequently deals with geographically scattered personal data between multiple government locations and organizations. As digital technologies advance, public administration is increasingly relying on collaborative intelligence w...

(This article belongs to the Special Issue Information and Future Internet Security, Trust and Privacy II)
  • Article
  • Open Access
12 Citations
6,461 Views
21 Pages

27 December 2022

Critical infrastructure, such as water treatment facilities, largely relies on the effective functioning of industrial control systems (ICSs). Due to the wide adoption of high-speed network and digital infrastructure technologies, these systems are n...

(This article belongs to the Section Communications)
  • Article
  • Open Access
781 Views
44 Pages

31 August 2026

Transformer architectures, originally developed for language modeling, have been increasingly applied to time-series forecasting, but deploying them on sensitive data such as patient vital signs, financial records, or energy use raises privacy risks...

  • Article
  • Open Access
375 Views
23 Pages

4 June 2026

Graph representation learning models inherently capture structural and attribute correlations, which may lead to significant privacy risks under attribute inference attacks. Existing privacy-preserving methods mainly focus on post hoc suppression of...

  • Article
  • Open Access
1 Citations
3,152 Views
22 Pages

31 December 2024

This paper presents an approach to protecting deep neural network privacy on edge devices using ARM TrustZone. We propose a selective layer protection technique that balances performance and privacy. Rather than executing entire layers within the Tru...

(This article belongs to the Special Issue Advances in IoT Security)
  • Article
  • Open Access
738 Views
20 Pages

The Geometry of Privacy: A Two-Stage Analysis of Generative Membership Inference in Federated Learning

  • Borja Arroyo Galende,
  • Patricia A. Apellániz,
  • Alejandro Almodóvar,
  • Silvia Uribe and ,
  • Federico Álvarez and
  • Juan Parras
  • + 1 author+ 0 author

We study Membership Inference Attack (MIA) risk in Federated Learning through a two-stage lens that separates (i) whether a target client’s contribution is detectable after aggregation and system noise (Stage I: Signal Survival) from (ii) wheth...

  • Article
  • Open Access
1,227 Views
27 Pages

Understanding Differential Privacy in Decentralized Federated Learning: A Controlled Privacy–Utility Comparison

  • Alsharif Hasan Mohamad Aburbeian,
  • Manuel Fernández-Veiga,
  • Ana Fernández-Vilas,
  • Majdi Owda and
  • Amani Yousef Owda

16 September 2026

Centralized Federated Learning (FL) enables collaborative model training without sharing raw data. Differential privacy (DP) is widely used to protect sensitive information in FL; however, its behavior in decentralized environments remains poorly und...

(This article belongs to the Special Issue Privacy-Preserving and Secure Machine Learning)
  • Article
  • Open Access
19 Citations
4,909 Views
21 Pages

20 October 2023

With the development of deep learning, image recognition based on deep learning is now widely used in remote sensing. As we know, the effectiveness of deep learning models significantly benefits from the size and quality of the dataset. However, remo...

(This article belongs to the Topic AI and Data-Driven Advancements in Industry 4.0)
  • Article
  • Open Access
282 Views
29 Pages

Privacy-Preserving Federated Learning with Layer 2 Blockchain Anchoring for Auditable Clinical Trial Eligibility Screening

  • Andrada Cristina Artenie,
  • Catalin Daniel Morar,
  • Călin-Adrian Popa and
  • Ovidiu Gheorghe Moldovan

19 September 2026

Matching patients to clinical trials with large language models is technically feasible, but the prevailing methodology fine-tunes commercial models through external interfaces, transmitting sensitive patient records to third parties, and the resulti...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
11 Citations
4,352 Views
25 Pages

19 February 2025

The Internet of Things (IoT) is developing quickly, which has led to the development of new opportunities in many different fields. As the number of IoT devices continues to expand, particularly in transportation and healthcare, the need for efficien...

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
  • Article
  • Open Access
10 Citations
4,709 Views
13 Pages

Federated Learning with Dynamic Model Exchange

  • Hannes Hilberger,
  • Sten Hanke and
  • Markus Bödenler

Large amounts of data are needed to train accurate robust machine learning models, but the acquisition of these data is complicated due to strict regulations. While many business sectors often have unused data silos, researchers face the problem of n...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
302 Views
41 Pages

From Inference to Attack: AI-Driven BFI Forgery Against Unknown MU-MIMO Schedulers via TD-MoE

  • Yusheng Chen,
  • Xiaoyu Zhao,
  • Guanxiong Shen,
  • Tao Guo and
  • Ying Wan

15 September 2026

Compressed beamforming feedback information (BFI) reduces feedback overhead in multi-user multiple-input multiple-output (MU-MIMO) systems, but it also exposes the feedback signal that drives user scheduling and precoding. This paper studies whether...

(This article belongs to the Section Microwave and Wireless Communications)
  • Article
  • Open Access
4 Citations
2,444 Views
22 Pages

Novel Federated Graph Contrastive Learning for IoMT Security: Protecting Data Poisoning and Inference Attacks

  • Amarudin Daulay,
  • Kalamullah Ramli,
  • Ruki Harwahyu,
  • Taufik Hidayat and
  • Bernardi Pranggono

31 July 2025

Malware evolution presents growing security threats for resource-constrained Internet of Medical Things (IoMT) devices. Conventional federated learning (FL) often suffers from slow convergence, high communication overhead, and fairness issues in dyna...

  • Article
  • Open Access
61 Citations
13,376 Views
36 Pages

8 April 2010

The proposed mechanism for jamming attack detection for wireless sensor networks is novel in three respects: firstly, it upgrades the jammer to include versatile military jammers; secondly, it graduates from the existing node-centric detection system...

(This article belongs to the Special Issue Wireless Sensor Network and Its Application in Advanced Computer Science)
  • Article
  • Open Access
208 Views
40 Pages

18 October 2026

Deep-learning compiler transformations can change security-sensitive inference decisions without changing trained model parameters. Critical compilation strictness measures the smallest set of enforceable source/reference-semantic sites whose protect...

(This article belongs to the Special Issue Novel Approaches for Deep Learning in Cybersecurity, 2nd Edition)

of 11