A2-DIDM: Privacy-Preserving Accumulator-Enabled Auditing for Decentralized Identity of DNN Model

TY - JOUR

T1 - A2-DIDM

T2 - Privacy-Preserving Accumulator-Enabled Auditing for Decentralized Identity of DNN Model

AU - Xie, Tianxiu

AU - Gai, Keke

AU - Yu, Jing

AU - Zhu, Liehuang

N1 - Publisher Copyright: © 2026 IEEE.

PY - 2026/7/1

Y1 - 2026/7/1

N2 - 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 an Accumulator-enabled Auditing for Decentralized Identity of DNN Model (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.

AB - 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 an Accumulator-enabled Auditing for Decentralized Identity of DNN Model (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.

KW - Decentralized identity

KW - blockchain

KW - deep neural network (DNN)

KW - identity audit

KW - intellectual property protection

UR - https://www.scopus.com/pages/publications/105036876409

U2 - 10.1109/TDSC.2026.3685897

DO - 10.1109/TDSC.2026.3685897

M3 - Article

AN - SCOPUS:105036876409

SN - 1545-5971

VL - 23

SP - 8555

EP - 8571

JO - IEEE Transactions on Dependable and Secure Computing

JF - IEEE Transactions on Dependable and Secure Computing

IS - 4

ER -