Buchumschlag

Towards Understanding and Enhancing Security of Proof-of-Training for DNN Model Ownership Verification

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chang, Yijia, Jiang, Hanrui, Lin, Chao, Huang, Xinyi, Weng, Jian
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control
von: Xu, Chaohui, et al.
Veröffentlicht: (2025)

PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking
von: Deng, Haiyu, et al.
Veröffentlicht: (2025)

iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
von: Xiong, Zixun, et al.
Veröffentlicht: (2025)

DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing
von: Qiao, Ting, et al.
Veröffentlicht: (2025)

False Claims against Model Ownership Resolution
von: Liu, Jian, et al.
Veröffentlicht: (2023)

Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices
von: Xie, Xueshuo, et al.
Veröffentlicht: (2024)

FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
von: Shao, Shuo, et al.
Veröffentlicht: (2025)

ChainMarks: Securing DNN Watermark with Cryptographic Chain
von: Choi, Brian, et al.
Veröffentlicht: (2025)

SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
von: Wang, Yingjia, et al.
Veröffentlicht: (2025)

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
von: Shao, Shuo, et al.
Veröffentlicht: (2022)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
von: Shao, Shuo, et al.
Veröffentlicht: (2024)

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents
von: Li, Jiaqi, et al.
Veröffentlicht: (2026)

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
von: Hossain, Ismail, et al.
Veröffentlicht: (2026)

Towards Provable (In)Secure Model Weight Release Schemes
von: Yang, Xin, et al.
Veröffentlicht: (2025)

A Comparative Analysis of DNN-based White-Box Explainable AI Methods in Network Security
von: Arreche, Osvaldo, et al.
Veröffentlicht: (2025)

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
von: Rafid, Mohammad Ishzaz Asif, et al.
Veröffentlicht: (2025)

RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
von: Xu, Yang, et al.
Veröffentlicht: (2024)

On the (In)Security of LLM App Stores
von: Hou, Xinyi, et al.
Veröffentlicht: (2024)

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
von: Hou, Xinyi, et al.
Veröffentlicht: (2025)

PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
von: Gai, Keke, et al.
Veröffentlicht: (2025)

VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
von: Liao, Guofu, et al.
Veröffentlicht: (2025)

Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification
von: Han, Shanshan, et al.
Veröffentlicht: (2023)

Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems
von: Sharma, Gauri, et al.
Veröffentlicht: (2025)

A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms
von: Acharya, Nirajan, et al.
Veröffentlicht: (2026)

Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformation
von: Jiang, Yukun, et al.
Veröffentlicht: (2024)

ATLAS: AI-Assisted Threat-to-Assertion Learning for System-on-Chip Security Verification
von: Tashdid, Ishraq, et al.
Veröffentlicht: (2026)

CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
von: Li, Yiming, et al.
Veröffentlicht: (2025)

Towards Trustworthy AI: Secure Deepfake Detection using CNNs and Zero-Knowledge Proofs
von: Islam, H M Mohaimanul, et al.
Veröffentlicht: (2025)

Towards Automating Blockchain Consensus Verification with IsabeLLM
von: Jones, Elliot, et al.
Veröffentlicht: (2026)

Optimized Ensemble Model Towards Secured Industrial IoT Devices
von: Injadat, MohammadNoor
Veröffentlicht: (2024)

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
von: Dai, Muzhi, et al.
Veröffentlicht: (2025)

Towards more Practical Threat Models in Artificial Intelligence Security
von: Grosse, Kathrin, et al.
Veröffentlicht: (2023)

Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
von: Wang, Haodi, et al.
Veröffentlicht: (2024)

Watermarking Graph Neural Networks via Explanations for Ownership Protection
von: Downer, Jane, et al.
Veröffentlicht: (2025)

Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
von: Yang, Guang, et al.
Veröffentlicht: (2026)

Towards Effective Complementary Security Analysis using Large Language Models
von: Wagner, Jonas, et al.
Veröffentlicht: (2025)

A Survey: Towards Privacy and Security in Mobile Large Language Models
von: Xu, Honghui, et al.
Veröffentlicht: (2025)

Towards Small Language Models for Security Query Generation in SOC Workflows
von: Muzammil, Saleha, et al.
Veröffentlicht: (2025)

A2-DIDM: Privacy-preserving Accumulator-enabled Auditing for Distributed Identity of DNN Model
von: Xie, Tianxiu, et al.
Veröffentlicht: (2024)

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
von: Zhang, Jiawen, et al.
Veröffentlicht: (2025)