Enhancing Network Privacy through Secure Multi-Party Computation in Cloud Environments

Published: Feb. 23, 2024

Secure multi-party computation (SMPC) in cloud environments is an efficient method for preserving customer privacy networked applications. Multi-Party Computation enables many events to do interactive calculations safely and a designated manner, while keeping their data concealed from one another. The parties partition the calculation into smaller sub-tasks that are amenable encryption. They then perform of shared result using cryptographic protocols such as holomorphic encryption, Yao's protocol, verifiable codes. These techniques enable service providers preserve confidentiality clients' activities also allowing third audit verify accuracy computations. This solution offers superior level security compared traditional client-server model, environment can be continuously analyzed altered real-time. SMPC numerous advantages public-key infrastructure (PKI) solutions. because encryption decryption occur within protocol itself, eliminating need external key management certification. On average, greatly improve environments.

Language: Английский

---

Deep Learning in Cybersecurity: A Hybrid BERT–LSTM Network for SQL Injection Attack Detection

IET Information Security, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 16

Published: April 5, 2024

In the past decade, cybersecurity has become increasingly significant, driven largely by increase in threats. Among these threats, SQL injection attacks stand out as a particularly common method of cyber attack. Traditional methods for detecting mainly rely on manually defined features, making detection outcomes highly dependent precision feature extraction. Unfortunately, approaches struggle to adapt sophisticated nature attack techniques, thereby necessitating development more robust strategies. This paper presents novel deep learning framework that integrates Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) networks, enhancing attacks. Leveraging advanced contextual encoding capabilities BERT sequential data processing ability LSTM proposed model dynamically extracts word sentence-level subsequently generating embedding vectors effectively identify malicious query patterns. Experimental results indicate our achieves accuracy, precision, recall, F1 scores 0.973, 0.963, 0.962, 0.958, respectively, while ensuring high computational efficiency.

Language: Английский

---

Intelligent two-phase dual authentication framework for Internet of Medical Things

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 12, 2025

The Internet of Medical Things (IoMT) has revolutionized healthcare by bringing real-time monitoring and data-driven treatments. Nevertheless, the security communication between IoMT devices servers remains a huge problem because inherent sensitivity health data susceptibility to cyber threats. Current solutions, including simple password-based authentication standard Public Key Infrastructure (PKI) approaches, typically do not achieve an appropriate balance low computational overhead, resulting in possibility performance bottlenecks increased vulnerability attacks. To overcome these limitations, we present intelligent two-phase dual framework that improves sensor-to-server environments. During registration phase, our is based on Elliptic Curve Diffie-Hellman (ECDH) for rapid key exchange, during communication, uses Advanced Encryption Standard Galois Counter Mode (AES-GCM) encrypt securely. efficiency proposed was rigorously tested through simulations evaluated encryption-decryption time, cost, latency, packet delivery ratio. resilience also against man-in-the-middle, replay, brute force results show encryption/decryption time reduced over 45%, overall cost 45.38%, latency 28.42% existing approaches. Furthermore, achieved high ratio strong defense threats maintaining confidentiality integrity medical across networks. However, approach doesn't affect functionality IoT while enhancing security, which makes it ideal integration option systems.

Language: Английский

---

Fraud-BERT: transformer based context aware online recruitment fraud detection

Deleted Journal, Journal Year: 2025, Volume and Issue: 28(1)

Published: Feb. 6, 2025

Language: Английский

---

Homomorphic Encryption and Collaborative Machine Learning for Secure Healthcare Analytics

Security and Privacy, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 13, 2024

ABSTRACT With the advent of Internet Things (IoT), conventional healthcare system has evolved into a smart system, offering intelligent prognosis and diagnosis services. However, as sector embraces technological advances, concerns about privacy security critical patient data have become more prevalent. Due to adversarial attacks on traditional machine learning (ML), these systems is increasingly at risk. Collaborative (CML) homomorphic encryption (HE) recently viable approaches circumvent challenges systems. Inspired by staggering benefits CML HE, this research article examines different cryptographic techniques that enable computations encrypted while delving fundamental ideas HE. Simultaneously, it explores various frameworks for highlights their potential decentralized model training. The paper also critically analyses integrating HE with CML, insights safe aggregation, guaranteeing privacy, performance optimization use in environments. Further, we delved pragmatic scenarios actual implementations, illustrating how unified framework can improve cooperative Lastly, presented case study evaluates ML algorithms, such k‐nearest neighbors (KNN), random forest (RF), support vector (SVM), logistic regression (LR), secure analytics. results show KNN had best accuracy 76.5%, RF SVM having an 76%. LR 73.5%, which lower than all other models. These findings offer insightful information selecting models take trade‐off between precision, recall, F1 score account. This helps researchers make well‐informed selections classification work securing

Language: Английский

---