mlsanityData to 14 Oct 2026

Towards Provable (In)Secure Model Weight Release Schemes

arXiv 2506.19874 ↗First posted 23 Jun 2025cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 22 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

13 of 22 references.

References · 13

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2024Tamper-Resistant Safeguards for Open-Weight LLMscited by 138
  5. 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 96
  6. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 51
  7. 2023PUMA: Secure Inference of LLaMA-7B in Five Minutescited by 48
  8. 2024Double-I Watermark: Protecting Model Copyright for LLM Fine-tuningcited by 21
  9. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 19
  10. 2024ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Modelscited by 16
  11. 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 14
  12. 2025CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systemscited by 4
1 more
  1. 2024Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendationcited by 0