Low-altitude aerial networks play an increasingly critical role in urban logistics, emergency response, and intelligent airspace management. These networks must ensure reliable identity authentication while addressing privacy, efficiency, and security challenges. Traditional authentication mechanisms—such as PKI-based certificates and remote identification—either overexpose identity data or lack support for flexible attribute disclosure. Moreover, existing anonymous credential (AC) schemes, though offering privacy, often incur high computational and communication costs and exist vulnerable to replay attacks. To address these limitations, we proposeDVA-ACLF(Designated Verifier Asymmetric Anonymous Credential Scheme for Low-Altitude Flight), a lightweight credential system tailored for UAVs. DVA-ACLF leverages an efficient MAC-based construction combined with non-interactive zero-knowledge proofs to enable selective attribute disclosure without relying on pairings. It supports designated verification to prevent credential misuse and replay. Experimental results show that DVA-ACLF reduces credential size by 49% (2720 bits vs. 5369 bits in Idemix) and mitigates the linear growth of credential size with respect to attribute count observed in CL and BBS+ schemes. It requires only four single-base and$2(k-l)$double-base exponentiations on UAVs, where$k$is the number of selected attributes and$l$is the number of disclosed attributes—both typically small. These features make DVA-ACLF a strong candidate for secure, efficient, and privacy-preserving authentication in low-altitude flight applications.
Deny Prasetyo, Siska Narulita, Ahmad Jurnaidi Wahidin, Rosalina Yani Widiastuti · 7 authors
This study introduces a trust centric machine learning framework designed to improve decision making reliability and security in decentralized digital service ecosystems. Traditional machine learning models often focus on accuracy and efficiency but fail to address the challenges of trust and security in decentralized environments. In contrast, the proposed framework integrates dynamic trust indicators and employs Federated Learning (FL) to ensure privacy while enhancing decision making performance. The framework also incorporates Zero Knowledge Proofp based Verifiable Machine Learning (ZKP-VML), which ensures transparency and security without compromising sensitive data. Through continuous real time trust assessments, the framework adapts to changing conditions, improving the accuracy and reliability of decisions in environments where participants may not fully trust each other. The application of this framework in autonomous vehicles and IoT networks demonstrated its ability to make robust, secure decisions, even in complex and uncertain scenarios. The framework’s ability to incorporate both trust and security into its decision making processes sets it apart from traditional models, which typically do not address the trustworthiness of data or participants. This research highlights the importance of integrating trust and security into machine learning models, particularly in decentralized systems, and offers a robust solution to trust management challenges. However, challenges such as scalability and computational efficiency remain, and future work should focus on enhancing these aspects, along with exploring the framework's applicability in other decentralized domains like finance or supply chain management. The integration of privacy preserving technologies and improvements in adversarial robustness are also potential areas for future research.
Abdullah Ayub Khan, Asif Ali Laghari, Hamad Almansour, Teerath Kumar · 7 authors
Wearable health technology has revolutionized remote monitoring and personalized healthcare by allowing real-time surveillance of patient health measurements and vital signs. However, their widespread acceptance is hampered by issues with security, privacy preservation, data protection, and interoperability. Blockchain Technology (BT), in particular Zero-Knowledge Proofs (ZKPs) and smart contracts, present a viable way to enhance the privacy, provenance, and integrity of wearable health data. This paper proposes a BT-enabled system that guarantees decentralized, unforged data management, transparency, immutability, and dynamic traceability for wearable health devices, particularly smartwatches with biosensors. To evaluate the effectiveness of the proposed work, the main performance-related metrics-latency, throughput, computational overhead, security robustness, and scalability-are looked at. The experiment's simulated findings show that BT integration is effective, with a 99.33% improvement in data integrity and protection. Automated access control protocols demonstrate data protection by utilizing smart contracts, and ZKPs guarantee verifiable data exchanges without jeopardizing patient privacy. These results demonstrate improved interoperability, decreased processing time, and increased security in comparison to comparable cutting-edge centralized platforms.
We present the Mazari Bidirectional Architecture, a cryptographic framework providing end-to-end privacy guarantees for computation systems employing homomorphic encryption (HE), differential privacy (DP), and zero-knowledge proofs (ZK). The architecture comprises two complementary orderings: Y.I.N. Mazari Ordering (DP→ZK→HE) for secure data submission and Y.A.N.G. Mazari Ordering (VERIFY→DISAGGREGATE→DECRYPT→DENOISE) for secure result retrieval. Through exhaustive permutation analysis, we prove that among all possible orderings for each direction, exactly one ordering in each direction is secure—and these orderings are mathematical duals. The Y.I.N. ordering prevents information leakage during data submission, while the Y.A.N.G. ordering prevents timing side-channel attacks during result retrieval. This paper provides comprehensive coverage of all implementation variations, security proofs, and robustness analysis to establish technical foundations for privacy-preserving computation research.
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic operations, such as dropout, create an ambiguity surface where attackers can mask malicious manipulations as natural random variance, granting them plausible deniability. Consequently, existing logging mechanisms cannot verify whether stochastic values were generated and applied honestly without exposing sensitive training data. To close this integrity gap, we introduce Verifiable Dropout, a privacy-preserving mechanism based on zero-knowledge proofs. We treat stochasticity not as an excuse but as a verifiable claim. Our approach binds dropout masks to a deterministic, cryptographically verifiable seed and proves the correct execution of the dropout operation. This design enables users to audit the integrity of stochastic training steps post-hoc, ensuring that randomness was neither biased nor cherry-picked, while strictly preserving the confidentiality of the model and data.
Fully Homomorphic Encryption (FHE) enables computation on encrypted data with end-to-end confidentiality; however, its practical adoption remains limited by substantial computational costs...
Federated Learning (FL) enables distributed model training while preserving data privacy; however, it remains vulnerable to poisoning attacks and lacks computational integrity. Recent solutions integrating Zero-Knowledge Proofs (ZKPs) and blockchain have successfully established process-level verifiability but suffer from prohibitive computational overhead due to the requirement of generating cryptographic proofs for every local update. To address this efficiency bottleneck, this paper proposes Pro-ZkFL, a reputation-aware probabilistic verification framework. Unlike deterministic approaches that verify every transaction, Pro-ZkFL utilizes Verifiable Random Functions (VRF) on-chain to dynamically select a subset of clients for auditing based on their historical reputation scores. We design a dual-commitment scheme where clients submit lightweight cryptographic commitments for every round but generate heavy ZKPs only when challenged. Experimental results on FashionMNIST and CIFAR-10 demonstrate that Pro-ZkFL reduces computational overhead by approximately 82 % and gas costs by 73 % compared to full-verification baselines while maintaining a 99 % detection rate against persistent adversaries, offering a scalable trade-off between security and efficiency.
Elif Nur Kucur, Tolga Büyüktanır, Muharrem Ugurelli, Kazım Yıldız
Privacy-preserving machine learning (PPML) constitutes a core element of responsible AI by supporting model training and inference without exposing sensitive information. This survey presents a comprehensive examination of the major cryptographic PPML techniques and introduces a unified taxonomy covering technical models, verification criteria, and evaluation dimensions. The study consolidates findings from both survey and experimental works using structured comparison tables and emphasizes that recent research increasingly adopts hybrid and verifiable PPML designs. In addition, we map PPML applications across domains such as healthcare, finance, Internet of Things (IoT), and edge systems, indicating that cryptographic approaches are progressively transitioning from theoretical constructs to deployable solutions. Finally, the survey outlines emerging trends—including the growth of zero-knowledge proofs (ZKPs)-based verification and domain-specific hybrid architectures—and identifies practical considerations that shape PPML adoption in real systems.
Healthcare AI needs large, diverse datasets, yet strict privacy and governance constraints prevent raw data sharing across institutions. Federated learning (FL) mitigates this by training where data reside and exchanging only model updates, but practical deployments still face two core risks: (1) privacy leakage via gradients or updates (membership inference, gradient inversion) and (2) trust in the aggregator, a single point of failure that can drop, alter, or inject contributions undetected. We present zkFL-Health, an architecture that combines FL with zero-knowledge proofs (ZKPs) and Trusted Execution Environments (TEEs) to deliver privacy-preserving, verifiably correct collaborative training for medical AI. Clients locally train and commit their updates; the aggregator operates within a TEE to compute the global update and produces a succinct ZK proof (via Halo2/Nova) that it used exactly the committed inputs and the correct aggregation rule, without revealing any client update to the host. Verifier nodes validate the proof and record cryptographic commitments on-chain, providing an immutable audit trail and removing the need to trust any single party. We outline system and threat models tailored to healthcare, the zkFL-Health protocol, security/privacy guarantees, and a performance evaluation plan spanning accuracy, privacy risk, latency, and cost. This framework enables multi-institutional medical AI with strong confidentiality, integrity, and auditability, key properties for clinical adoption and regulatory compliance.
This paper introduces an AI based Privacy Broker (AIBPB), a unified framework that combines blockchain, zero knowledge proofs, attribute based encryption, and differential privacy to enable verifiable and compliant data sharing in regulated environments. The system automatically interprets high level policies such as GDPR, HIPAA, and CCPA, and synthesizes optimized proof strategies through a multi objective cost privacy model. The architecture blends off chain cryptographic computation with on chain verification to balance privacy and transparency. Simulation based experiments demonstrate a 3.2 times improvement in proof generation latency, a 7.8 times reduction in information disclosure, and regulatory satisfaction rates exceeding 95% compared to baseline approaches. The results show that AI driven proof orchestration can significantly enhance scalability, compliance automation, and privacy protection in blockchain based systems.
The traditional credit scoring industry, dominated by a few centralized bureaus, suffers from opacity, data insecurity, and a lack of user-controlled data sovereignty. This paper introduces Zk-Cred, a novel decentralized protocol designed to address these challenges by leveraging a unique combination of Fully Homomorphic Encryption (FHE), Zero-Knowledge Proofs (ZKPs), and W3C Verifiable Credentials (VCs). Zk-Cred empowers individuals to generate a verifiable, privacy-preserving credit score without revealing their underlying financial data to any third party. The protocol’s core mechanism involves users encrypting their financial data client-side using an FHE scheme. A decentralized network of nodes then executes a publicly auditable credit scoring model on this encrypted data, computing a score that is only ever decrypted by the user. The user can then generate a ZKP to prove the correctness of the computation and receive a tamper-proof VC representing their creditworthiness. This VC can be presented to financial service providers, such as DeFi lending platforms or traditional institutions, for instant verification. By synthesizing these cryptographic primitives, Zk-Cred offers a new paradigm for credit scoring that is transparent, secure, and user-centric, with significant potential to enhance fairness and access in the global fintech ecosystem.
Bharath M. B, Ashwni S S, Mamatha M, Sowjanya S · 6 authors
With increasing dependence on AI for medical imaging diagnostics, privacy concerns and strict regulations continue to restrict data sharing across healthcare institutions. To address this, we propose a novel framework that enables cross-institutional collaboration without compromising sensitive patient information. Our system integrates federated learning with advanced privacy-preserving techniques, including homomorphic encryption, secure aggregation, differential privacy, and zero-knowledge proofs. Hospitals retain their data locally and contribute encrypted, noise-added model updates, ensuring that raw data never leaves the premises. Secure aggregation and encryption prevent any entity, including the central server, from accessing individual contributions. Differential privacy introduces mathematically bounded noise to mitigate risks from inversion and membership attacks. Meanwhile, zero-knowledge proofs allow clients to verify the legitimacy of their training process and updates without revealing internal computations or data. This layered privacy defense effectively counters gradient inversion, model poisoning, and membership inference attacks, all while maintaining strong diagnostic performance. Evaluated on real-world medical imaging datasets, our method balances accuracy with compliance to privacy laws like HIPAA and GDPR. The proposed architecture offers a scalable and trustworthy approach to enable AI-driven diagnostics across hospitals, ensuring patient confidentiality is never compromised.
The increasing amount of heterogeneous enterprise data has catalysed an expedient requirement of confiding, scalable, and privacy-preserving analytics structures. When data is distributed among various stakeholders, traditional data lake houses are prone to data integrity, provenance, and governance problems as well as secure model training. This paper seeks to overcome these difficulties by introducing a Trustworthy Data Lakehouse Architecture which combines Federated Learning (FL) with Blockchain-enabled governance to enhance safe, auditable and regulation compliant data analytics. The framework designed includes a built-in metadata layer, decentralized model-training pipeline, immutable ledger, based on blockchain and data provenance, and the privacy protection mechanisms of differential-privacy. Multi-organization collaboration without raw data exchange is possible thanks to Federated Learning, and end-to-end trust is ensured by blockchain which supports consensus-based validation, lineage tracking based on tamper-proof, and access control with smart-contracts. Experimental analysis is used to show that there are data reliability, model accuracy, latency, and confidentiality improvements over traditional centralized lake houses. The presented solution opens up a strong base of constructing transparent, secure and scaled out data ecosystems applicable to finance, healthcare, supply chain among other sensitive areas.
Federated Learning (FL) has emerged as a distributed paradigm enabling multiple participants to collaboratively train machine learning models without sharing their raw data. By keeping data local, FL mitigates many privacy risks inherent to centralized learning architectures. However, despite this promise, recent research has revealed that exchanged gradients can still leak sensitive information about local datasets. Furthermore, most existing approaches rely on strong and often unrealistic trust assumptions toward the central server, while providing no means to verify whether privacy-preserving mechanisms have been correctly enforced. These limitations expose a critical gap between theoretical privacy guarantees and their practical implementation in real-world federated systems.This thesis investigates how to bridge this gap by combining differential privacy (DP) with cryptographic and verifiability protocols to achieve verifiable and trust-reduced federated learning. First, we explore the use of additive homomorphic encryption to protect client updates and minimize reliance on a trusted aggregator. Second, we introduce a non-interactive verifiability protocol based on zk-SNARKs and cryptographic hashes, allowing third parties to prove and verify the correct application of DP without revealing sensitive information. Finally, we propose ProoFed, a distributed framework that leverages secret sharing to decentralize noise generation and integrate verifiable aggregation proofs in zero knowledge, thereby eliminating single points of trust.
Rapid digital transformation across financial, e-commerce, and decentralized platforms has amplified the need for secure, transparent, and resilient transaction systems. Conventional security mechanisms often fail to address sophisticated cyber threats, identity fraud, and evolving attack patterns, highlighting the necessity for integrated technological solutions. The convergence of Blockchain and Artificial Intelligence (AI) establishes a robust framework that combines immutable, decentralized ledger structures with adaptive, intelligent analytics. Blockchain ensures transactional integrity, data provenance, and decentralized trust, while AI facilitates real-time anomaly detection, predictive risk scoring, and automated decision-making. This synergy enhances digital identity management, strengthens access control, and mitigates fraud by enabling continuous monitoring, behavioral analysis, and transparent verification processes. Applications extend to secure payments, smart contracts, cross-border transactions, and decentralized finance ecosystems, demonstrating improved operational efficiency, scalability, and resilience. The chapter also explores privacy-preserving computation, federated learning, and explainable AI frameworks to ensure ethical and accountable deployment of intelligent transaction systems. By integrating structural security with predictive intelligence, Blockchain-aided AI frameworks establish a next-generation foundation for secure digital transactions, fostering trust, regulatory compliance, and systemic reliability across global digital networks.
Financial institutions are currently faced with suffering never experienced before as they strive to guarantee the privacy of data and address the demands of regulation to report and cooperate in machine learning. This paper proposes PrivChain-AI, a novel blockchain-based federated learning system designed to facilitate secure and privacy-preserving financial reporting and access control. The proposed framework will integrate three key components: differential privacy, homomorphic encryption, and smart contract-based governance, enabling cooperative model training across financial institutions while preventing the leakage of sensitive information. PrivChain-AI is a hierarchical design that incorporates permissioned consensus protocols and utilises zero-knowledge proof verification to authenticate transactions. It has been demonstrated that the performance is higher than that of the actual financial data, with an outcome of 94.7% accuracy in fraud recognition at the cost of e-differentiation privacy, where ϵ = 1.0. It is 40% faster in terms of communication overhead and ensures regulatory compliance, as it features immutable audit trails. The analysis of performances reveals that a privacy preservation metric improves by 78%, and access control granularity is improved by 62% compared to the current state-of-the-art approaches. The PrivChain-AI paradigm introduced provides a new analytical model for safe, collaborative finance, meeting the highest standards and ensuring compliance with relevant regulatory jurisdictions.
Damilare E. Bakare, Adekemi Olawunmi Amoo, Mary T. Onifade
The health insurance sector has been facing many challenges recently, such as fraudulent activities in insurance claims, data breaches, and high transaction costs, particularly with existing systems built on the Ethereum network, which negatively affect its efficiency and effectiveness.These challenges undermine the trust and financials of insurance providers while compromising the privacy of the patient's health records.To address this issue, this study proposes a conceptual framework that uses zero-knowledge proof within the blockchain system and is deployed on the Polygon Network for its low transaction fees and higher throughput.The proposed model allows the verification of an insurance claim without revealing sensitive patient health records, ensuring privacy while preventing fraudulent activities.In this conceptual design, the hospital can issue verifiable proof of treatment, appointment, and bill that shows the validity of the insurance claim without revealing the underlying health record to the insurer.This study, therefore, contributes to supporting research in decentralized applications for healthcare insurance by presenting a conceptual model and comprehensively analyzing the feasibility, rather than a full-scale implementation.It also emphasizes the need to preserve privacy in sensitive domains and the potential benefits of blockchain and ZKP integration.In conclusion, the research's findings show that, in theory, integrating ZKP with blockchain technology can enhance healthcare insurance processes in terms of reliability, efficiency, privacy, and security.However, further research and practical development are required to realize and evaluate a fully operational system.
With the rapid development of geological blockchains and Internet of Things-based data acquisition technologies, massive amounts of heterogeneous data are constantly emerging. However, this data is stored in a distributed manner across different organizational or business blockchains. Data sharing among multiple geological blockchains faces numerous challenges, either exposing sensitive data during verification or lacking effective authorization mechanisms. Therefore, how to achieve fine-grained access control and privacy protection across multiple blockchains has become a critical issue that must be addressed in geological data sharing. In this paper, we propose GeoCross, a cross-chain geological data sharing framework that enables fine-grained authorization management and privacy protection. First, GeoCross provides a hierarchical hybrid encryption mechanism that uses symmetric encryption for geological data protection and ciphertext-policy attribute-based encryption to enable flexible cross-chain access policies. Second, we integrate a Groth16-based zero-knowledge proof mechanism, which allows a chain to verify the existence, integrity, and accessibility of off-chain data without revealing the content. Furthermore, we introduce a Reputation-based Non-interactive Relay node Selection protocol (RNRS), which enhances the trustworthiness and fairness of cross-chain routing. Finally, we implement GeoCross in a multi-chain Hyperledger Fabric environment and evaluate its performance under real-world workloads. Results show that Groth16 verification requires only three bilinear pairings, achieving a throughput of up to 390 tps on a single chain and 1550 tps in a concurrent multi-chain environment. Even with 50% malicious nodes, the RNRS protocol still maintains a success rate of over 91%. These results demonstrate that GeoCross provides an efficient and practical solution for secure and privacy-preserving cross-chain geological data sharing.
We present the Y.I.N. Mazari Architecture, an 8-pillar privacy-preserving federated learning system built around a novel cryptographic ordering: DP→ZK→HE (Differential Privacy →Zero-Knowledge Proof →Homomorphic Encryption) applied to federated learning gradients. The name Y.I.N. honors Yanis, Ilyan, and Neylia Mazari, while embodying the core principle that Your Information Never leaves your control.We identify a fundamental barrier in privacy-preserving federated learning: the inability to verify that participants correctly applied differential privacy noise while maintainin computational efficiency. The Y.I.N. Mazari Ordering resolves this barrier through a specific sequencing of cryptographic operations.This paper extends the classical architecture into the quantum domain through the QFED-MAZARI system,introducing the Mazari Quantum Ordering: QDP→MUA→DQEM(Quantum Differential Privacy →Manifold Unitary Aggregation →Distributed Quantum Error Mitigation). Experimental results demonstrate 99.37% model accuracy with 223× speed improvement in classical systems, while the quantum extension achieves 91.9% accuracy with 40–50% communication reduction. Together, the classical and quantum architectures establish a comprehensive 30-year intellectual property runway.
Financial crime detection faces unparalleled challenges as criminal networks exploit digital payment channels, cryptocurrency platforms, and cross-border transaction systems outside traditional monitoring frameworks. In this respect, AFCI introduces a novel framework for federated machine learning, regulatory reasoning engines, and real-time risk propagation analytics to build unified global privacy-preserving anti-crime intelligence ecosystems. The framework lets organizations train collaborative models with decentralized institutions, safely aggregating information from multiple parties without sharing sensitive transaction data by means of secure aggregation protocols and differential privacy mechanisms. Large language models coupled with knowledge graphs automate the processes of regulatory interpretation and rule generation, and graph neural networks enable the detection of coordinated criminal activities on a large scale in transaction networks through temporal message passing mechanisms. Reinforcement learning agents continuously optimize detection policies to balance the identification of genuine threats against the goal of minimizing false alarms. The framework bridged critical gaps in cross-border compliance coordination and empowered institutions to develop shared detection capabilities in support of data localization requirements and an array of diverse regulatory frameworks. Long-term security of privacy-preserving federated computation would be guaranteed with post-quantum cryptography. This convergence of advanced technologies allows next-generation financial crime prevention systems to remain effective against evolving criminal methodologies while preserving fundamental privacy rights.
The proliferation of Internet of Things (IoT) and Cyber-Physical Systems (CPS) has ushered in an era of unprecedented data generation and automation. However, this interconnectivity introduces profound security and privacy challenges, particularly concerning the centralized aggregation of sensitive data for machine learning model training. Traditional cloud-centric approaches are vulnerable to single points of failure, data breaches, and privacy infringements. This paper investigates the synergistic integration of two transformative technologies-Blockchain and Federated Learning (FL)-as a robust framework to address these critical shortcomings. Federated Learning enables the collaborative training of machine learning models across distributed devices without centralizing raw data, thereby preserving data locality and privacy. Blockchain technology complements this by providing a decentralized, immutable, and transparent ledger to orchestrate the FL process securely. It facilitates trustworthy model aggregation, verifiable participant contribution, and resilient consensus mechanisms, mitigating risks such as model poisoning and malicious node attacks. The integration establishes a verifiable and auditable trail for all transactions within the FL lifecycle, from participant selection to global model updates. This research delineates the architectural principles of this integration, analyzes its efficacy in enhancing security and privacy for IoT and CPS, and discusses prevailing challenges and future research trajectories aimed at realizing a secure and trustworthy intelligent infrastructure.
Tan Gürpinar, Mehmet Akif Gulum, Melanie Martinelli
Enterprises today face increasing threats from cyberattacks, supply chain disruptions, and systemic market risks, making the enhancement of organizational resilience through advanced risk management frameworks increasingly critical. Traditional approaches often struggle to balance data privacy, cross-organizational collaboration, and real-time adaptability. While distributed ledger technologies (DLTs) initially enabled cryptocurrencies, they have evolved into a foundational infrastructure for decentralized AI applications. This study investigates how decentralized AI techniques, particularly federated learning, can support joint risk management processes in enterprise networks. First, a comprehensive review of decentralized AI methods is conducted to identify approaches suitable for enterprise risk management. Next, expert interviews are used to contextualize these insights, highlighting practical considerations, organizational challenges, and adoption constraints. Building on the literature and expert feedback, a decentralized framework is developed to allow organizations to securely share risk-related insights while preserving data privacy and control over proprietary information. The framework is validated through a technical prototype, combining architectural design with empirical proof-of-concept experiments on federated learning benchmarks. Results demonstrate the feasibility of achieving near-centralized model accuracy under privacy constraints, while also highlighting communication and governance issues that need to be addressed in real-world deployments. The study presents a structured comparison of decentralized AI techniques and a validated concept for enhancing supply chain risk prediction, fraud detection, and operational continuity across enterprise networks.
The need for strong cybersecurity frameworks in the healthcare industry has increased due to the Internet of Medical Things (IoMT) devices and electronic health records (EHRs) exponential growth. This paper presents HealthSentinel-ZKP, a novel framework that leverages federated neuro-symbolic deep learning and zero-knowledge blockchain to secure electronic health data. In contrast to earlier models, HealthSentinel-ZKP combines CNNs, Transformers, and symbolic reasoning for multi-perspective intrusion detection. Federated learning and zero-knowledge proof mechanisms protect data privacy. Using an immutable ZKPenhanced blockchain, the system guarantees GDPR-compliant auditing and has a dual-stream anomaly detection architecture. HealthSentinel-ZKP is a next-generation healthcare cybersecurity paradigm, as demonstrated by experimental results on benchmark datasets that demonstrate superior performance in zero-day attack detection and privacy preservation.