| FA | https://www.furaffinity.net/user/shangxian/ |
| NewGrounds | https://shangxian.newgrounds.com/ |
| PixelFed.de | https://pixelfed.de/i/web/profile/707295669178916666 |
| Languages | Italian, English, German (currently learning so feel free to correct me) |
Some photos I took of this crow who is recently visiting my area. My heart is always filled with joy whenever I see him/her.
The Whore of Blahbylon
rqsd+).Complete Security and Privacy for AI Inference in Decentralized Systems
Hongyang Zhang, Yue Zhao, Claudio Angione, Harry Yang, James Buban, Ahmad Farhan, Fielding Johnston, Patrick Colangelo
https://arxiv.org/abs/2407.19401 https://arxiv.org/pdf/2407.19401
arXiv:2407.19401v1 Announce Type: new
Abstract: The need for data security and model integrity has been accentuated by the rapid adoption of AI and ML in data-driven domains including healthcare, finance, and security. Large models are crucial for tasks like diagnosing diseases and forecasting finances but tend to be delicate and not very scalable. Decentralized systems solve this issue by distributing the workload and reducing central points of failure. Yet, data and processes spread across different nodes can be at risk of unauthorized access, especially when they involve sensitive information. Nesa solves these challenges with a comprehensive framework using multiple techniques to protect data and model outputs. This includes zero-knowledge proofs for secure model verification. The framework also introduces consensus-based verification checks for consistent outputs across nodes and confirms model integrity. Split Learning divides models into segments processed by different nodes for data privacy by preventing full data access at any single point. For hardware-based security, trusted execution environments are used to protect data and computations within secure zones. Nesa's state-of-the-art proofs and principles demonstrate the framework's effectiveness, making it a promising approach for securely democratizing artificial intelligence.
The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial for complex tasks, present challenges in scalability, reliability, and potential misuse. Decentralized systems offer a solution by distributing workload and mitigating central points of failure, but they introduce risks of unauthorized access to sensitive data across nodes. We address these challenges with a comprehensive framework designed for responsible AI development. Our approach incorporates: 1) Zero-knowledge proofs for secure model verification, enhancing trust without compromising privacy. 2) Consensus-based verification checks to ensure consistent outputs across nodes, mitigating hallucinations and maintaining model integrity. 3) Split Learning techniques that segment models across different nodes, preserving data privacy by preventing full data access at any point. 4) Hardware-based security through trusted execution environments (TEEs) to protect data and computations. This framework aims to enhance security and privacy and improve the reliability and fairness of multimodal AI systems. Promoting efficient resource utilization contributes to more sustainable AI development. Our state-of-the-art proofs and principles demonstrate the framework's effectiveness in responsibly democratizing artificial intelligence, offering a promising approach for building secure and private foundational models.
I’m so annoyed by the appification of services…
No, I won’t install your stupid app just to book a haircut, to see the balance in my meal card, or to be notified when my vehicle is ready to leave the garage.
Especially if your stupid app needs a ton of irrelevant permissions, weights 250 MB, keeps itself always busy in the background and bugs me with notifications!
Develop a fucking universal web app which can be used by pretty much anyone anywhere immediately and without leaving a trail of binary droppings.
arXiv cs.CR bot
Thomas
tripu
Serena is still in #yeg 🍞