Towards Provable (In)Secure Model Weight Release Schemes
Recent secure weight release schemes claim to enable open-source model distribution while protecting model ownership and preventing misuse. However, these approaches lack rigorous security foundations and provide only informal security guarantees. Inspired by established works in cryptography, we formalize the security of weight release schemes by introducing several concrete security definitions. We then demonstrate our definition's utility through a case study of TaylorMLP, a prominent secure weight release scheme. Our analysis reveals vulnerabilities that allow parameter extraction thus showing that TaylorMLP fails to achieve its informal security goals. We hope this work will advocate for rigorous research at the intersection of machine learning and security communities and provide a blueprint for how future weight release schemes should be designed and evaluated.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Robust Provably Secure Image Steganography via Latent Iterative Optimization
We propose a robust and provably secure image steganography framework based on latent-space iterative optimization. Within this framework, the receiver treats the transmitted image as a fixed reference and iteratively re…
Image CompressionTowards Secure and Practical Machine Learning via Secret Sharing and Random Permutation
With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical ap…
BIG-bench Machine LearningPrivacy PreservingPrivacy Preserving Deep LearningSecure Identification for Gaussian Channels and Identification for Multi-Antenna Gaussian Channels
New applications in modern communications are demanding robust and ultra-reliable low latency information exchange such as machine-to-machine and human-to-machine communications. For many of these applications, the ident…
FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature
Federated learning allows multiple parties to collaborate in learning a global model without revealing private data. The high cost of training and the significant value of the global model necessitates the need for owner…
Federated LearningInformation-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
On-device federated learning (FL) enables privacy-preserving and personalized model training on resource-constrained devices such as smartphones and IoT nodes. To reduce communication cost, sign-based methods (e.g., sign…
Federated Learning