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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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 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...
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...
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...
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...
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...
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...
Under non-independent and identically distributed (Non-IID) conditions, significant variations exist in local model updates across clients and training phases during the collaborative modeling process of differential privacy federated learning (DP-FL...
Machine unlearning in federated graph learning must satisfy the multi-level indistinguishability requirement of the deletion of a target node being undetectable at the level of the global model, of the unlearning client’s local model, and of ev...
Compressed-TinyML pipelines apply distillation, quantization and pruning to fit lightweight anomaly detectors onto resource-constrained sensor nodes. Such frameworks are routinely called privacy-aware on the strength of on-device inference or noisy f...
Hierarchical text classification consists of classifying text documents into a hierarchy of classes and sub-classes. Although Artificial Neural Networks have proved useful to perform this task, unfortunately, they can leak training data information t...
Federated learning (FL) has been broadly adopted in both academia and industry in recent years. As a bridge to connect the so-called “data islands”, FL has contributed greatly to promoting data utilization. In particular, FL enables disjo...
The utilization of machine learning models is extensive in a wide array of significant applications. However, their vulnerability to security and privacy attacks is a serious concern, for example, for the protection of financially sensitive data such...
Electroencephalography (EEG)-based brain–computer interface (BCI) systems pose significant privacy risks, as EEG data remain vulnerable to inference and reconstruction attacks. Conventional privacy-preserving techniques, including data anonymiz...
While Federated Learning (FL) and Split Learning (SL) aim to uphold data confidentiality by localized training, they remain susceptible to adversarial threats such as model poisoning and sophisticated inference attacks. To mitigate these vulnerabilit...
Federated Learning is identified as a reliable technique for distributed training of ML models. Specifically, a set of dispersed nodes may collaborate through a federation in producing a jointly trained ML model without disclosing their data to each...
This paper reviews the privacy and security challenges posed by open-source artificial intelligence (AI) models. The increased use of open-source machine learning models, while beneficial for resource efficiency and collaboration, has introduced sign...
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...
Ensuring privacy protection in machine learning is crucial for handling sensitive information, particularly in ethical case studies within computer engineering. Traditional information extraction methods often expose private data to risks such as mem...
UAV-assisted cyber–physical–social systems increasingly use visual analytics for disaster response, infrastructure monitoring, traffic management, and safety-oriented situational awareness. Raw aerial imagery can expose faces, license pla...
Insider threats remain one of the most challenging security risks in modern enterprises due to their subtle behavioral patterns and the difficulty of distinguishing malicious intent from legitimate activity. This paper presents a unified and adaptive...
Auditability and regulatory compliance are increasingly required for deploying large language models (LLMs). Prior work typically targets isolated stages such as training or unlearning and lacks a unified mechanism for verifiable accountability acros...
The security of AI models poses significant challenges, as sensitive user information can potentially be inferred from the models, leading to privacy breaches. To address this, machine unlearning methods aim to remove specific data from a trained mod...
Federated learning (FL) has been widely used in both academia and industry all around the world. FL has advantages from the perspective of data security, data diversity, real-time continual learning, hardware efficiency, etc. However, it brings new p...
The integration of artificial intelligence into remote patient monitoring (RPM) offers significant benefits for proactive and continuous healthcare, but also raises critical concerns regarding privacy, integrity, and robustness. Federated Learning (F...
Images used in intelligent graphite ore sorting can reveal grade-related visual and spatial information. Selective encryption reduces the cost of full-image protection and preserves nonsensitive background regions, but the number, location, and shape...
Large language models (LLMs) have shown remarkable skills across various activities, including text generation and code synthesis. Their widespread applicability, however, raises substantial concerns about security, privacy, and possibly misuse. Of r...
Strong differential privacy often collapses utility in transformer-based time-series forecasting because noise is injected directly into high-dimensional gradients (e.g., DP-SGD), severely corrupting the optimization process. We introduce Low-Dimensi...
Cyber–Physical Systems (CPSs) are increasingly vulnerable to Distributed Denial-of-Service (DDoS) attacks, which can disrupt critical operations and compromise system safety. Although deep learning (DL) techniques are widely adopted for cyberat...
Generative AI, including large language models (LLMs), has transformed the paradigm of data generation and creative content, but this progress raises critical privacy concerns, especially when models are trained on sensitive data. This review provide...
This research aims to find an optimal balance between privacy and performance in forecasting mental health sentiment. This paper investigates federated learning (FL) augmented with a novel data obfuscation (DO) technique, where synthetic data is used...
In recent years, machine learning algorithms are increasingly dependent on large volumes of data for their training, including personal data, while at the same time the law has strengthened the right of individuals to have such data deleted, thus cre...
of 2