Skyward Secure: Advancing Drone Data-Sharing in 6G with Decentralized Dataspace and supported Technologies

Journal of Parallel and Distributed Computing, Journal Year: 2025, Volume and Issue: unknown, P. 105040 - 105040

Published: Jan. 1, 2025

Language: Английский

---

Privacy in Federated Learning

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 22, 2025

Federated learning (FL) represents a significant advancement in distributed machine learning, enabling multiple participants to collaboratively train models without sharing raw data. This decentralized approach enhances privacy by keeping data on local devices. However, FL introduces new challenges, as model updates shared during training can inadvertently leak sensitive information. chapter delves into the core concerns within FL, including risks of reconstruction, inversion attacks, and membership inference. It explores various privacy-preserving techniques, such differential (DP) secure multi-party computation (SMPC), which are designed mitigate these risks. The also examines trade-offs between accuracy privacy, emphasizing importance balancing factors practical implementations. Furthermore, it discusses role regulatory frameworks, GDPR, shaping standards for FL. By providing comprehensive overview current state this aims equip researchers practitioners with knowledge necessary navigate complexities federated environments. discussion highlights both potential limitations existing privacy-enhancing offering insights future research directions development more robust solutions.

Language: Английский

---

Navigating the nexus of AI and IoT: A comprehensive review of data analytics and privacy paradigms

Internet of Things, Journal Year: 2024, Volume and Issue: 27, P. 101318 - 101318

Published: Aug. 3, 2024

Integrating Artificial Intelligence (AI) with the Internet of Things (IoT) has propelled technological innovation across various industries. This systematic literature review explores current state and future trajectories AI in IoT, a particular focus on emerging trends intelligent data analysis privacy protection. The proliferation IoT devices, marked by voluminous generation, reshaped processing methods, providing actionable insights for informed decision-making. While previous reviews have offered valuable insights, they often must comprehensively address multifaceted dimensions AI-driven landscape. aims to bridge this gap systematically examining existing acknowledging limitations past studies. study uses meticulous approach guided established methodologies achieve aim. chosen methodology ensures rigour validity review, aligning PRISMA 2020 guidelines reviews. serves as comprehensive guide researchers, practitioners, policymakers, offering into landscape paving way research directions. identified challenges provide resource navigating evolving domain fostering balanced, secure, sustainable advancement dynamic field. Our shows that integrating improves operational efficiency, service personalisation, data-driven decisions healthcare, manufacturing, urban management. Real-time machine learning algorithms edge computing solutions are set revolutionise improving system responsiveness privacy. However, increasing concerns about security emphasise need new regulatory frameworks protection technologies ensure ethical adoption technologies.

Language: Английский

---

A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy

Future Internet, Journal Year: 2024, Volume and Issue: 16(10), P. 374 - 374

Published: Oct. 15, 2024

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling decentralized model training across multiple devices while preserving data privacy. However, the nature of FL introduces significant security challenges, making it vulnerable to various attacks targeting models, data, and This survey provides comprehensive overview defense strategies against these attacks, categorizing them into defenses privacy attacks. We explore pre-aggregation, in-aggregation, post-aggregation defenses, highlighting their methodologies effectiveness. Additionally, delves advanced techniques such homomorphic encryption differential safeguard sensitive information. The integration blockchain technology for enhancing environments is also discussed, along with incentive mechanisms promote active participation among clients. Through this detailed examination, aims inform guide future research developing robust frameworks systems.

Language: Английский

---

Secure Multi-Party Computation (SMPC) Protocols and Privacy

Advances in information security, privacy, and ethics book series, Journal Year: 2024, Volume and Issue: unknown, P. 190 - 214

Published: July 12, 2024

This chapter explores the growing field of secure multi-party computation (SMPC), an important part modern cryptography that protects privacy in group computing tasks. It does this by looking at their architectural designs, security models, ways to make them more efficient, and cross-domain uses. goes into detail about complex architecture cryptographic methods support SMPC, such as homomorphic encryption sharing secrets, which protect integrity data computations involving than one person. also talks strong models can against a wide range threats, well algorithmic design protocol implementation efficient. In addition, it how SMPC be used many different areas, like healthcare, banking, AI, stresses need follow rules GDPR. The ends with look ahead, talking new challenges trends are coming up.

Language: Английский

---

Edge AI for Real-Time Anomaly Detection in Smart Homes

Future Internet, Journal Year: 2025, Volume and Issue: 17(4), P. 179 - 179

Published: April 18, 2025

The increasing adoption of smart home technologies has intensified the demand for real-time anomaly detection to improve security, energy efficiency, and device reliability. Traditional cloud-based approaches introduce latency, privacy concerns, network dependency, making Edge AI a compelling alternative low-latency, on-device processing. This paper presents an AI-based framework that combines Isolation Forest (IF) Long Short-Term Memory Autoencoder (LSTM-AE) models identify anomalies in IoT sensor data. system is evaluated on both synthetic real-world datasets, including temperature, motion, consumption signals. Experimental results show LSTM-AE achieves higher accuracy (up 93.6%) recall but requires more computational resources. In contrast, IF offers faster inference lower power consumption, it suitable constrained environments. A hybrid architecture integrating proposed balance achieving sub-50 ms latency embedded platforms such as Raspberry Pi NVIDEA Jetson Nano. Optimization strategies quantization reduced time by 76% 35%. Adaptive learning mechanisms, federated learning, are also explored minimize cloud dependency enhance data privacy. These findings demonstrate feasibility deploying real-time, privacy-preserving, energy-efficient directly edge devices. can be extended other domains buildings industrial IoT. Future work will investigate self-supervised transformer-based detection, deployment operational settings.

Language: Английский

---

Privacy-preserving and Verifiable Federated Learning with weighted average aggregation in edge computing

Journal of Network and Computer Applications, Journal Year: 2025, Volume and Issue: unknown, P. 104201 - 104201

Published: May 1, 2025

Language: Английский

---

A Comprehensive Survey on Generative AI Solutions in IoT Security

Electronics, Journal Year: 2024, Volume and Issue: 13(24), P. 4965 - 4965

Published: Dec. 17, 2024

The influence of Artificial Intelligence in our society is becoming important due to the possibility carrying out analysis large amount data that increasing number interconnected devices capture and send as well making autonomous instant decisions from information machines are now able extract, saving time efforts some determined tasks, specially cyberspace. One key issues concerns security this cyberspace controlled by machines, so system can run properly. A particular situation, given heterogeneous special nature environment, case IoT. limited resources components such a network distributed topology make these types environments vulnerable many different attacks leakages. capability Generative generate contents autonomously learn predict situations be very useful for automatically instantly, significantly enhancing IoT systems. Our aim work provide an overview Intelligence-based existing solutions diverse set try anticipate future research lines field delve deeper.

Language: Английский

---

Ensuring Security Continuum from Edge to Cloud : Adaptive Security for IoT-based Critical Infrastructures using FL at the Edge

2021 IEEE International Conference on Big Data (Big Data), Journal Year: 2024, Volume and Issue: unknown, P. 4921 - 4929

Published: Dec. 15, 2024

Language: Английский

---