NeuroZK - Cyborg parachain's ZK verification layer #2393
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
the
admin-review
keeganquigley
requested changes
Sep 20, 2024
There was a problem hiding this comment.
Hi @beekay2706 thanks for the follow up application. Quick question, is there a reason you are trying to modify the original application? Usually we don't modify applications after they have been merged. Can you add this info to the new one instead?
keeganquigley
added
changes requested
github-actions
bot
added
the
admin-review
|
Hi @keeganquigley , Thank you for your response, and I apologize for the oversight. A new line was unintentionally added when I merged some changes from w3f's main into our local branch. This has been corrected in the latest commit. |
keeganquigley
requested changes
Sep 20, 2024
|
|
||
| As part of our previous application, we delivered CyberDock, a product line focused on helping users deploy dockerized containers into our edge server network. We are now focusing on expanding this approach to a new product line called NeuroZK, which will enable AI apps to run Inference Engines backed by ZK proofs. | ||
|
|
||
| Users can easily run GPU based inference engines in our crowdsoruced GPU network, with compute integrity verified using a ZK SNARK proof that proves that the inference algorithm was executed with 100% accuracy without revealing the actual inference algorithm nor the query or result data. |
There was a problem hiding this comment.
- What is the process for generating ZK proofs to verify the correctness of AI inference computations?
- How are ZK proofs verified on-chain, and what are the computational costs involved?
|
|
||
| Through this process, we identified the need for having a much simpler provider onboarding experience, so we are developing a custom node implementation called Cyborg worker nodes using which providers can connect their resources to the Cyborg parachain just by downloading and installing an executable file on their VMs. This also aligns with our focus to launch a plug and play hardware series called 'Cyborg miners' that directly connects to the parachain like an ASIC miner. | ||
|
|
||
| Consequently, we will be delivering a ZK based offchain compute verification system, that validates the integrity of executing pre-trained AI models for decentralized AI inferencing on crowdsourced GPUs. For this grant we will use ZK and TEE to uphold data privacy in the system. |
There was a problem hiding this comment.
- What security guarantees does the ZK SNARK system provide against attacks such as proof forgery or false verification?
- How resilient is the ZK SNARK system to changes in the AI model or inference environment?
|
|
||
| Though Cyborg and the [Phala Network](https://phala.network/) share aspirations of decentralized computing within the Polkadot/Kusama environment, our technical paths and business aspirations are distinct. Phala Network provides off-chain compute infrastructure for smart contract-based applications by enabling users to integrate 'phat' contracts with their existing smart contract logic. While Cyborg is focused on creating utility for web2 applications. | ||
|
|
||
| Another related project appears to be [Wetee](https://github.com/wetee-dao), which employs a comparable technical architecture utilizing TEEs to safeguard user privacy. However, their specific market focus is currently untraceable. We are developing products for a validated market that has already attracted interest from various AI applications and 50 edge data center providers to join the network once it goes live. |
There was a problem hiding this comment.
Are you able to provide proof, if not publicly then privately, about these 50 data center partnerships?
keeganquigley
removed
the
admin-review
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Project Abstract
This application is a follow up from our successful grant delivery
Cyborg Network is an AI-centric blockchain designed specifically to handle AI workloads, utilizing crowdsourced off-chain compute infrastructure verified with Zero-Knowledge (ZK) Proofs to enhance data privacy and security in AI models.
We are developing a platform for managing AI compute resources (both training and inference) with strategic partnerships across web2 and web3 domains. Continuing on our previous delivery, we are motivated to create a ZK verification layer to improvise the compute verification process with better privacy.
Grant level
Application Checklist
project_name.md).@_______:matrix.org(change the homeserver if you use a different one)