The interplay between the advancements in quantum computing techniques and the adoption of the distributed learning approach pose an enormous challenge to conventional cryptographic authentication protocols. Traditional public key systems and federated learning (FL) authentication methods based on the hardness of solving the integer factorization problem or discrete logarithms become inefficient due to the existence of Shorâs algorithm. This paper gives a detailed review of the latest research efforts toward the development of efficient and secure privacy-preserving FL authentication methods based on Post-Quantum Cryptography (PQC). In particular, we present the state-of-the-art of three schemes, namely, PQBFL (Post-Quantum Blockchain-based Federated Learning), ZKFL-PQ (Zero-Knowledge Federated Learning with Lattice-Based Encryption), and Enhanced EAADE for vehicular networks. It is shown that lattice-based authentication is both computationally efficient (signing times of around 0.65 ms) and robust against quantum attacks. Our proposed hybrid scheme is comprised of ML-KEM for key encapsulation, ML-DSA-65 for digital signatures, and Zero-knowledge proof for gradient integrity verification. The empirical evaluation shows a reduction of 44.96% in the computation cost and 22.16% in the communication cost relative to the class.
Ms. Anushka Prasad Joshi, Prof. Sachin Bhosale, Dr. Shubhangi Gunjal, Dr. Anand Khatri
Abstract: With real estate markets digitalizing at a remarkable pace, there's a growing â and largely unmet â need for machine learning systems that can harness multi-institutional data without putting privacy or regulatory standing at risk. In this paper, we present a Privacy-Preserving Federated Learning (PP-FL) framework built specifically for digital real estate ecosystems. Our approach lets distributed stakeholders â property agencies, government land registries, financial institutions, and PropTech platforms â collaboratively train predictive models without ever pooling their raw transaction or personal records in one place. We've designed the system around three interlocking privacy layers: a DP-SGD-based differential privacy optimizer, a homomorphic encryption scheme for gradient transmission, and a secure multi-party computation protocol to safeguard intermediate model states. On top of that, a blockchain-backed audit mechanism using zero-knowledge proofs provides verifiable, regulator-friendly compliance. When we tested the framework on a simulated dataset of 2.4 million real estate transactions spanning multiple institutional clients, it achieved 91.8% prediction accuracy â just 2.4 percentage points behind a fully centralized model â while holding the differential privacy budget to Δ = 0.5, cutting communication overhead by 65% relative to naive federated approaches, and satisfying both GDPR and RERA requirements. We believe these results make a strong case that high-utility, privacy-first collaborative learning is not just theoretically possible but practically deployable in today's real estate sector. Keywords: Federated Learning, Differential Privacy, Homomorphic Encryption, Real Estate Analytics, Secure Multi-Party Computation, Blockchain, GDPR Compliance, Data Sovereignty, PropTech, Zero-Knowledge Proofs.
Ensuring node labeling stability is critical for graph-based learning systems, directly impacting trust evaluation, node classification, and structure-aware inference in complex relational domains. Traditional manual annotation is costly and inconsistent, necessitating automated alternatives such as Large Language Models (LLMs). However, while LLM-assisted annotation improves efficiency, the reliability of node labeling remains a concern due to structural biases, particularly in unsupervised and semi-supervised learning settings. This dissertation systematically investigates the role of strong-tie structures in stabilizing label predictions across different node labeling paradigms, examining their influence on unsupervised trust prediction, defense against poisoning attacks in graph neural networks (GNNs), and LLM-based annotation. First, we analyze how strong-tie structures influence unsupervised trust prediction in decentralized systems and financial networks. Our study reveals that trust annotation propagates preferentially along strong ties, making it susceptible to targeted adversarial manipulations. By strategically modifying a minimal number of edges, an attacker can significantly alter trust/untrust label assignments, exposing vulnerabilities in existing trust prediction frameworks. Our analysis reveals that strong-tie structures are preferentially exploited by adversarial agents. Understanding these patterns provides deeper insight into the structural vulnerabilities of trust prediction systems and offers a basis for evaluating the robustness of different algorithms. Next, we extend our investigation to structural poisoning attacks in semi-supervised learning. Our findings show that poisoning behaviors exhibit clear structural preferences, targeting specific strong-tie patterns to maximize their impact on label propagation. This motivates our proposed Graph Adaptive Neural Network (GANN) framework, which dynamically adjusts propagation mechanisms based on fuzzy-theoretic strong-tie graphs (STiG). By integrating adaptive trust and risk zones, GANN mitigates the spread of adversarial noise while preserving high-confidence label prediction. Through structural decomposition and adaptive validation, our approach significantly strengthens defense mechanisms in poisoned graph environments. Finally, we propose CSA-LLM (Crowd-sourced homophily-ties-based graph annotation via large language models), which utilizes strong-tie graph structures to design LLM prompts that enhance annotation quality. By embedding structural priors in prompt engineering, CSA-LLM improves consistency in automated label generation, offering a scalable alternative to traditional manual annotation. This structured approach not only enhances annotation robustness, but also mitigates the inconsistencies introduced by structure-agnostic token generation, where LLMs generate labels based solely on textual prompts without considering graph topology. This dissertation provides a unified perspective on the impact of strong-tie structures across node labeling paradigms, bridging trust prediction, adversarial resilience, and LLM-assisted annotation. Our findings contribute to the development of attack-aware, structure-informed annotation frameworks, with implications for applications in social network security, financial fraud detection, recommendation systems, and decentralized finance (DeFi).
Federated Learning (FL) enables collaborative model training while preserving data privacy but relies on centralized aggregation servers, leading to issues such as lack of transparency, vulnerability to malicious updates, and single points of failure. This paper proposes a decentralized federated learning framework integrating blockchain technology and the InterPlanetary File System (IPFS) to eliminate central authority and enhance trust. Smart contracts deployed on the Ethereum Sepolia testnet manage model submission, validation, incentive distribution, and reputation tracking. Model updates are stored off-chain using IPFS, while their hashes are recorded on the blockchain to ensure integrity and immutability. A staking and slashing mechanism is introduced to encourage honest participation, where valid contributions are rewarded and malicious updates are penalized. A reputation system further evaluates participant reliability over time. The system is implemented using PyTorch, Solidity, Web3.py, and React.js. Experimental results demonstrate improved security, transparency, and efficient decentralized coordination, highlighting the feasibility of integrating federated learning with blockchain and decentralized storage for scalable and trustworthy machine learning applications.
Swati Sachan, Dale Fickett, Richard Buchinger, Theo Miller
Recent advances in error-corrected qubits have accelerated the timeline for practical quantum computing. It poses a threat to cryptographic primitives used to secure financial systems, government infrastructure, communication networks, and DeFi (Decentralized Finance) ecosystems. This paper introduces a post-quantum secure federated DeFi framework that enables inter-bank collaboration to improve the inclusivity of individuals underserved by local lenders due to limited financial histories. Multiple banks contribute encrypted information batches to a virtual server, where lattice-based Fully Homomorphic Encryption (FHE) enables end-to-end homomorphic computation. The server fuses local data-driven probabilistic assessments, expert beliefs, and verifiable evidence generated by the NASA-IBM Prithvi Geospatial Foundation Model (GFM), in encrypted format. Decentralized technologies are employed to ensure tamper-proof evidence and auditable accountability for all encrypted data exchanges between institutions and the server. The framework is tested on agricultural lending decisions for rural borrowers in Virginia.
Sixth-generation (6G) networks are expected to provide ubiquitous connectivity, AI-native orchestration, and seamless integration across terrestrial and non-terrestrial infrastructures. However, these capabilities introduce new privacy challenges related to the classification and protection of personal, quasi-personal, and non-personal data in complex data-driven environments. This paper presents a systematic review of 78 peer-reviewed studies published between 2019 and 2025. Following a PRISMA-based methodology, this review analyzes privacy-enhancing technologies (PETs), regulatory compliance frameworks, and architectural patterns for privacy preservation in 6G networks. The findings show that differential privacy (DP) and federated learning (FL) dominate current research, accounting for nearly 52% of the reviewed studies. Blockchain auditing and zero-knowledge proofs (ZKPs) collectively represent approximately 30%, while the remaining mechanisms, including physical-layer security (PLS), trusted execution environments (TEEs), homomorphic encryption (HE), secure multi-party computation (SMPC), and anonymization, account for roughly 18%. These mechanisms exhibit varying levels of privacy strength, utility preservation, latency, and energy cost. At the same time, evolving regulatory frameworks, including GDPR, PDPL, CCPA/CPRA, LGPD, and PIPL, increasingly extend privacy obligations to quasi-personal and aggregated data. Building on these findings, this paper proposes a unified taxonomy that clarifies the boundary between personal and non-personal data. It also provides a cross-layer mapping between PETs and compliance requirements across the Core/SBA, RAN, Edge/MEC, and NTN layers. Finally, this paper presents a forward-looking roadmap for 2025â2030, highlighting hybrid PET pipelines, post-quantum auditability, and AI-driven compliance automation as key directions for privacy-preserving 6G standardization.
The European Commission's April 2026 age verification framework, built on software-based Zero-Knowledge Proofs (ZKP) atop the European Digital Identity (EUDI) Wallet, fails to achieve its stated privacy guarantees due to a structural enrollment binding problem: any ZKP scheme whose trust root is a government identity credential inherits that credential's linkability at the point of issuance. This paper proposes a replacement architecture based on hardware bearer credentials â physically issued FIDO2 tokens whose identity binding is discarded immediately after issuance â combined with an anonymous hardware-handle revocation list, offline kiosk enrollment, and a self-funding economic model. The proposal is technically feasible with current production technology, financially viable at EU procurement scale, and operationally self-sustaining through a âŹ10 citizen co-payment at issuance plus a âŹ30 replacement fee. A cost model for national deployment using Italy as a case study demonstrates that the system requires near-zero net public expenditure. The primary novel contribution is a game-theoretic mechanism embedded in the replacement fee structure that renders secondary market trading of credentials economically irrational without requiring any surveillance of credential holders.
Data valuation is a foundational task in data marketplaces, where a Shapley-value attribution determines how a buyer's payment is distributed among data providers. Typically, the marketplace operator runs this attribution alone, requiring participants and external auditors to trust scores they cannot independently recompute on the underlying private data. While zero-knowledge proofs (ZKPs) can theoretically reconcile this conflict between privacy and verifiability, existing ZK valuation systems fail to scale to real-world marketplace demands due to prohibitive proving times or the requirement to disclose validation cohorts. We present ZK-Value, a practical, end-to-end ZK data-valuation system. Our solution bridges the scalability gap through a fully co-designed architecture: (1) LSH-Shapley, a locality-based valuation primitive that replaces expensive pairwise distance metrics with per-bucket collision counts; (2) ZK-LSH-Shapley, a tailored ZKP protocol that drastically reduces witness size by encoding these counts into bucket-level histograms rather than naive per-pair tensors; and (3) structural proof-system optimizations, specifically super-oracle batching and sparsity skipping. Evaluated across 12 standard datasets, ZK-Value delivers valuation quality on par with state-of-the-art baselines (within 0.033 AUROC of exact KNN-Shapley), while generating proofs in seconds to minutes and outperforming specialized ZK baselines by 12.6x to 68.1x in proving time, with verification in under 4.6 s.
The intricate and unpredictable nature of cryptocurrency markets has brought Bitcoin price prediction into the spotlight because of the relatively high volatility levels of cryptocurrencies. Conventional centralized machine learning solutions pose challenges on the issue of data privacy, security, and scalability, especially with financial applications. To respond to these issues, this paper outlines an overall execution of a federated learning system to predict Bitcoin prices. K-Nearest Neighbours, Decision Tree, Linear Regression, and Federated Long Short-Term Memory (FL-LSTM) model are federated, trained, and tested on past Bitcoin market data. Within the proposed framework, the process of model training is executed at each of several clients locally, and only model parameters or predictions are transmitted without data privacy. Experimental data reveal that classical federated machine learning models have poor performance in modelling complex price dynamics. Although Federated Linear Regression reflects similar goodness of-fit, the FL-LSTM proposed model is always associated with the lower prediction error and is highly close to the real price movements. Also, the FL-LSTM model is used to predict the short-term future, which proves that this model can be useful to anticipate future fluctuations in Bitcoin prices. The results affirm that federated learning, which has been combined with deep learning models, is a viable and privacypreserving solution in cryptocurrency prediction in a decentralized setting. Root Mean Square Error (RMSE) and$\mathbf{R}^{\mathbf{2}}$were used to measure the proposed models. The results of the experiment show that the FL-LSTM model possesses the lowest prediction error, and it is much closer to real Bitcoin price trends than the other federated models.
The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentralized model training without compromising local data privacy. As organizational data silos grow, deploying complex machine learning models across highly distributed edge networks becomes a critical infrastructural challenge. Standard FL implementations suffer from severe vulnerabilities related to adversarial gradient updates and computational bottlenecks at the aggregation layer. This paper presents a novel, end-to-end distributed architecture that hardens FL pipelines using advanced cryptographic verification and optimized big data processing frameworks. We introduce a Zero-Knowledge Proof (ZKP) wrapper that cryptographically validates node computations before global aggregation, neutralizing model poisoning attacks without inspecting raw gradients. Additionally, we evaluate the system's performance using extreme gradient boosting models optimized for distributed edge execution. We formalize the mathematical transformation of the machine learning loss functions into Rank-1 Constraint Systems (R1CS) suitable for succinct verification. Extensive experimental results demonstrate that our hybrid architecture achieves a 94.2\% accuracy retention under adversarial conditions while maintaining scalable throughput across 1,000 parallel distributed nodes, effectively bridging the gap between rigorous cryptographic security and high-performance distributed AI.
Electronic Healthcare Records (EHRs) provide distributed access to patient and doctor information through pervasive cloud-based storage. As this data is highly sensitive, robust privacy measures are essential to mitigate adversarial impacts. To ensure optimal privacy across multiple shared EHRs, this article proposes a Session-dependent Zero Knowledge Proof Technique (SZKPT). The framework identifies privacy breaches using two truth values: the first representing optimal session closure, and the second reflecting verification at each sharing instance. Both truth values are validated through iterated session validations, which are managed using a deep learning paradigm. During training, different combinations of truth values are employed to maximize privacy during data sharing, while iterative processes train consecutive validation instances to improve breach detection. Truth values are continuously updated to reflect the session closure and the most recent privacy verification. In practice, if either truth value equals zero, the session is suspended; otherwise, if truth values are valid in consecutive iterations, data sharing is delegated to the authorized user. The process is repeatted at regular intervals with updated truth values, ensuring continuous monitoring and adaptive privacy protection. The proposed technique is rigorously evaluated using key performance metrics, including access verification, computational complexity, privacy breach detection, verification time, and access delegation time. Results demonstrate that SZKPT effectively balances privacy preservation with usability, providing a reliable, scalable, and efficient solution for secure EHR management in cloud-based healthcare systems.
In IIoT situations, federated learning (FL) is a way to use industrial data that protects privacy. At the same time, adding blockchain to federated learning training makes it more trustworthy. But there are still some big problems with current blockchain-based FL frameworks: 1) The current consensus mechanisms don't do a good job of filtering out bad devices, which lets low-quality participants mess with global model training and make the model less robust; 2) Current privacy budget strategies are too simple, making it hard to find a balance between protecting privacy during statistical queries and gradient updates. Strong privacy protection lowers model accuracy, while weak protection doesn't protect against poisoning attacks. This paper proposes ShieldDFL, a blockchain-based federated learning framework with dual privacy protection and reputation-driven consensus, to solve these problems. This method uses a hybrid consensus mechanism based on LSTM-based reputation scoring to dynamically assess both short-term and long-term device contributions. This makes it possible to choose the best devices with accuracy. At the same time, it adds a new dual privacy budget mechanism that uses differential privacy for both statistical queries and gradient updates. This keeps privacy strong while keeping the model's performance high. The proposed method lowers the chances of bad devices getting into the consensus pool to 1.5%, lowers the success rates of SAR and BASR attacks to 5.8% and 2.1%, respectively, and keeps the model's accuracy high at 98.1% on MNIST and 87.6% on CIFAR-10. In general, the proposed framework does a good job of getting around the security and privacy problems that come with blockchain-based federated learning. It offers a fast and flexible way for decentralised and trustworthy collaboration in IIoT situations.
In the digital era, personal data is continuously collected, processed, and shared by organizations across various sectors. Traditional consent management systems suffer from centralization, opacity, and insufficient user control, making it difficult for individuals to track and enforce their data-sharing preferences. This paper presents ConsentChain, a decentralized consent governance protocol built on the Polygon blockchain. The system leverages Ethereum-compatible smart contracts to implement purpose-bound, time-limited, and user-revocable consent records, backed by an immutable on-chain audit trail. The architecture employs two core Solidity smart contractsâConsentManager and AccessControllerâsupported by a React-based frontend and MetaMask wallet integration. Comprehensive end-to-end testing demonstrates 18 of 18 test cases passing, validating the correctness of consent lifecycle management, access validation, role-based access control, and event logging. ConsentChain demonstrates that blockchain technology can provide a transparent, tamper-proof, and user-sovereign alternative to conventional consent management systems, with clear pathways toward enterprise adoption, multi-chain deployment, and zero-knowledge privacy extensions. Index TermsâBlockchain, Consent Management, Smart Contracts, Data Privacy, GDPR, Decentralized Systems, Ethereum, Polygon, Access Control, Audit Trail.
Healthcare data is among the most sensitive and frequently targeted information in the digital era. Existing centralised Electronic Health Record (EHR) systems are vulnerable to data breaches, unauthorised access, and single-point failures. This paper introduces a blockchain-based privacy-preserving framework for healthcare data management that integrates smart contracts, attribute-based encryption (ABE), and zero-knowledge proofs (ZKP) to ensure tamper-proof, role-gated data access. Our system is deployed on a permissioned Hyperledger Fabric network with a RESTful API gateway and a React-based patient portal. Experimental evaluations show that the proposed system achieves 99.2% access-control policy enforcement, reduces unauthorised access incidents to near zero, and maintains record retrieval latency under 180 ms at the 95th percentile. The framework also supports HIPAA and GDPR compliance through immutable audit trails and consent lifecycle management
<sec> <title>BACKGROUND</title> Self-sovereign identity (SSI) provides a decentralized approach to digital identity management, enabling individuals to control their personal data without reliance on centralized authorities. Blockchain technology offers a tamper-resistant and distributed infrastructure that can support secure and verifiable identity systems. In health care, where identity fragmentation, privacy risks, and interoperability challenges persist, blockchain-enabled SSI (BC-SSI) has been proposed as a potential solution. However, existing research remains heterogeneous, with varying levels of technical maturity and limited evidence of real-world deployment. </sec> <sec> <title>OBJECTIVE</title> This study conducts a scoping review to systematically map BC-SSI applications in health care and to analyze their application domains, development stages, study aims, targeted challenges, and technological infrastructures. In addition, this study aims to identify structural gaps in current research and assess the readiness of BC-SSI systems for clinical deployment. </sec> <sec> <title>METHODS</title> This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) methodology. A comprehensive literature search conducted between September 2024 and August 2025 identified 37 peer-reviewed studies that met predefined inclusion criteria. Data were extracted and synthesized using descriptive and thematic analyses across application areas, system maturity, technological components, and reported challenges. </sec> <sec> <title>RESULTS</title> The findings indicate that BC-SSI research in health care remains at an early stage of maturity, with most studies proposing conceptual models or prototype implementations and limited real-world validation. Applications predominantly focus on identity verification, credential management, and privacy-preserving data exchange across domains such as electronic health records, mobile health, and access control systems. Commonly used technologies include decentralized identifiers, verifiable credentials, smart contracts, and privacy-enhancing mechanisms such as zero-knowledge proofs and selective disclosure. Despite rapid technical development, persistent challenges include interoperability limitations, governance gaps, usability concerns, and insufficient integration with health care infrastructures. Notably, a structural gap was identified between technological capability and system-level readiness for clinical deployment. </sec> <sec> <title>CONCLUSIONS</title> BC-SSI technologies demonstrate potential for enabling secure, interoperable, and patient-centric identity management in health care. However, current research is predominantly technology-driven and lacks sufficient system-level validation. This study highlights the need for integrated architectural approaches, governance frameworks, and real-world evaluation to bridge the gap between conceptual innovation and clinical implementation. Advancing BC-SSI toward health care adoption will require coordinated progress across technical, organizational, and regulatory dimensions. </sec>
Abstract Federated learning (FL) has emerged as a paradigm-shifting approach to distributed machine learning, enabling multiple participants to collaboratively train models without exposing raw data. However, conventional federated learning architectures remain susceptible to a broad spectrum of security and privacy threats, including model poisoning, gradient inversion, inference attacks, and Byzantine faults. This paper presents a unified and robust frameworkâ Secure and Privacy-Preserving Federated AI (SPFA) â that integrates differential privacy, homomorphic encryption, secure multi-party computation, Byzantine fault tolerance, and zero-knowledge proofs into a unified, production-grade architecture. We formally analyze the threat model, prove privacy guarantees under the ( Δ , ÎŽ )-differential privacy framework, and demonstrate Byzantine resilience under partial adversarial participation. Extensive experiments on heterogeneous data distributions across image classification, natural language processing, and medical diagnosis benchmarks demonstrate that SPFA achieves model accuracy within 2.3% of centralized baselines while providing provable Δ = 1.0 privacy with a communication overhead of only 18% above standard FedAvg. To the best of our knowledge, our framework is among the first to consolidate all five protection layers into a unified, deployable system with formal analysis and an open-source reference implementation. The relevance of SPFA extends to privacy-sensitive applications in healthcare, cybersecurity, distributed edge computing, and smart city analytics.
Incentive (or point) systems are widely deployed across industries such as retail, tourism, and finance to enhance customer loyalty and create benefits for service providers. However, their operation typically requires the collection and processing of sensitive customer data, leading to significant privacy concerns. Existing privacy-preserving incentive systems predominantly rely on bilinear pairings and the discrete logarithm assumption, which, while efficient in classical settings, are vulnerable to quantum adversaries and thus lack long-term security guarantees. To address this limitation, we present LatInc, a practical lattice-based privacy-preserving incentive system. LatInc integrates state-of-the-art lattice-based signatures with efficient protocols, the ABDLOP commitment, and efficient lattice zero-knowledge proofs, achieving a robust balance between post-quantum security and efficiency. Relying on the hardness of the MLWE and MSIS problems, we formally prove that LatInc achieves unforgeability, anonymity, and framing-resistance in the random oracle model. We implement a demo of the system and evaluate its performance on a standard laptop platform. Experimental results show that the communication overheads for the Earning and Spending protocols are approximately 99 KB and 140 KB, respectively, with execution times of 610 ms and 900 ms, highlighting significant efficiency gains over previous lattice-based incentive constructions.
Introduction: Intelligent room systems are experiencing a surge in demand within the Healthcare 4.0 ecosystem. The integration of Federated Learning (FL) and Data-Centric AI has led to substantial enhancements in the predictive capabilities of machine learning models while maintaining data privacy. However, centralized aggregation in FL remains a single point of failure and is vulnerable to poisoning attacks. Methods: This paper presents a novel, privacy-preserving architecture for Ambient Intelligence (AmI) that integrates Distributed Ledger Technology (DLT). Results: We explicitly note that while DLT does not preemptively prevent the generation of poisoned gradients, it provides an immutable, cryptographically secure audit trail. This ensures the trustworthiness and traceability of model updates for post-hoc detection, strict accountability, and targeted model rollbacks. Discussion: By fusing Data-Centric AI for quality assurance with a Blockchain-enabled FL framework, we propose a scalable, low-cost solution for real-time patient monitoring in diverse economic settings.
Recent booming development of Generative Artificial Intelligence (GenAI) has facilitated model commercialization to reinforce the model performance, including licensing or trading Deep Neural Network (DNN) models. However, DNN model trading may violate the benefit of the model owner due to unauthorized replications or misuse of the model. Model identity auditing is a challenging issue in protecting DNN model ownership, and verifying the integrity and ownership of models is one of the critical obstacles. In this paper, we focus on the above issue and propose anAccumulator-enabledAuditing forDecentralizedIdentity of DNNModel (A2-DIDM) that utilizes blockchain and zero-knowledge techniques to protect data and function privacy while ensuring the lightweight on-chain ownership verification. The proposed model presents a scheme of identity records via configuring model weight checkpoints with zero-knowledge proofs, which incorporates predicates to capture incremental state changes in model weight checkpoints. Our scheme ensures both computational integrity and programmability in DNN training process so that the uniqueness of the weight checkpoint sequence in a DNN model is preserved. A2-DIDM also addresses privacy protections in decentralized identity. We systematically analyze the security and robustness of our proposed model and further evaluate the effectiveness and usability of auditing DNN model identities. The code is available athttps://github.com/xtx123456/A2-DIDM.git.