SMPC mp4 1x1.mp4

The new, state of the art SMPC system has enabled Worldcoin to securely delete its previous iris code system, including old iris codes.

The above content speaks only as of the date indicated. Further, it is subject to risks, uncertainties and assumptions, and so may be incorrect and may change without notice. A full disclaimer can be found in our Terms of Use and Important User Information can be found on our Risks page.

Applied research from the Worldcoin Foundation and TACEO, a team of cryptography engineers, has advanced the state of the art in biometric template protection and enabled the secure deletion of Worldcoin’s previous iris code system. 

Working within a field of cryptography known as secure multi-party computation (SMPC), Worldcoin and TACEO have applied recent advances in SMPC for Machine Learning to iris codes, which enable Worldcoin to determine an individual’s uniqueness. 

This new approach, which is open source and available in a Github repository, allows the iris codes to be individually encrypted into multiple different secret shares held by multiple parties. These parties can then work together to compute results over the secret information without learning anything about the secret itself. 

With this, World ID has achieved an unprecedented level of privacy protection for deduplication (verification of uniqueness) of biometric templates. After the migration of iris codes to the new SMPC system, the previous uniqueness-checking system, including old iris codes, was securely deleted.

John Daugmann (2004). How Iris Recognition Works. Pre-print.

 Secret sharing schemes can also be designed where the secret can be reconstructed with fewer than all shares, a so-called threshold amount. This is useful to protect against loss of shares. In the present version, we do not make use of a threshold and all shares are required.

Ronald Cramer, Ivan Bjerre Damgård, Jesper Buus Nielsen (2015). Secure Multiparty Computation and Secret Sharing. Cambridge.

Of course, one must always be wary of unintentional leakage in protocol design. For example, if there were two colleagues, each could easily compute the other's salary from the average and their own.

Kasra EdalatNejad, Wouter Lueks, Justinas Sukaitis, Vincent Graf Narbel, Massimo Marelli, Carmela Troncoso (2023). Janus: Safe Biometric Deduplication for Humanitarian Aid Distribution. Pre-print.

Toshinori Araki, Jun Furukawa, Yehuda Lindell, Ariel Nof, and Kazuma Ohara (2016) High-Throughput Semi-Honest Secure Three-Party Computation with an Honest Majority. Pre-print.

Payman Mohassel and Peter Rindal (2018). ABY3: A Mixed Protocol Framework for Machine Learning. Pre-print.

Remco Bloemen, Daniel Kales, Philipp Sippl, Roman Walch (2024). Large-Scale MPC: Scaling Private Iris Code Uniqueness Checks to Millions of Users. Pre-print.

Worldcoin Foundation unveils new SMPC system, deletes old iris codes 

After many migrations, Worldcoin can finally find its new permanent home in a place that can scale: World Chain.

Worldcoin is launching its own L2: World Chain. After many migrations within the Ethereum Ecosystem, Worldcoin can finally find its new permanent home in a place that can scale.

Finding a scalable home for Worldcoin

The core components of the Orb’s software are now publicly available on GitHub under an MIT/Apache 2.0 dual license.

World App is the first World ID-compatible wallet, created and operated by project contributor Tools for Humanity (TFH).

For a general overview of the need for proof of humanness, see Vitalik Buterin’s recent blog post.

Users can explicitly opt-in to giving the Worldcoin Foundation access to their images for the purposes of ensuring trust, safety, and improving the system.

The full suite of fraud detection measures extends beyond the Orb to the Orb’s backend and World App. For security reasons, the publicly available source code for today's release does not include all Orb software components related to fraud prevention.

The Orb OS build source will be included in a future release. See the release table for more information. 

The second control loop on the microcontroller helps stabilize the natural oscillations of the lens.

“Authentic” means the images are of a real human. Images displayed on a screen in front of the Orb, for example, will be rejected. These fraud checks are not included in the open source repositories. See the “Looking ahead: transparency and verifiability” section for more details.

See the whitepaper section, as well as Understanding Worldcoin Data Security Practices and Solving for Privacy. 

The individual’s public key is sent from World App to the Orb through the backend infrastructure. The backend does not need to be trusted because the public key’s hash is sent to the Orb directly via a QR code, which is used to verify the key before it’s used. 

This public key is generated by World App and only used for encrypting the Personal Custody data. Additional details are specified here.

Details on the further decentralization of this process can be found here.

Even the Orb can’t decrypt the Personal Custody package after it encrypts it. 

See the “Oracles: Orbs” section of Advancing Decentralization.

“Sensitive” code relates to fraud checking and tamper detection.

Worldcoin Foundation open sources core components of the Orb’s software

The work done by Reilabs and Worldcoin contributor TFH is a pivotal advancement in ensuring the robustness of the Worldcoin protocol.

Worldcoin, Reilabs mark blockchain security milestone with SMTB formal verification

The Worldcoin Foundation has announced the open sourcing of the project’s iris recognition pipeline, a new standard in open source end-to-end iris recognition systems.

The above content speaks only as of the date indicated. Further, it is subject to risks, uncertainties and assumptions, and so may be incorrect and may change without notice. A full disclaimer can be found in our Terms of Use and Important User Information can be found on our Risks page.
 

The Iris Recognition Inference System (IRIS) software repository is owned and maintained by the Worldcoin Foundation, the steward of the Worldcoin protocol; the repository is not affiliated with any other project or service provider.

Open sourcing the Worldcoin iris recognition pipeline

Outlining a path to a permissionless protocol owned and governed by all of humanity.

The goal of the Worldcoin project is to ingrain humanness and financial equitability in the global digital infrastructure. Grand challenges in the next decade are global income inequality, governance of existential risks and distinguishing humans from artificial intelligence. Humanity needs a protocol to solve these challenges. Worldcoin aims to be this protocol.

To succeed, Worldcoin must grow beyond its current community, to be built, owned and governed by all the people. You can join the community and help make the protocol robust by:

- joining the Community Grants Program
- reading the Worldcoin Whitepaper
- reviewing the Worldcoin Tech Tree

To become part of the global digital infrastructure, Worldcoin must be as robust, widespread and neutral as the internet itself. Any lesser standard is insufficient to effectively address the grand challenges. This has been a priority from day one, and much has already been achieved. To understand the challenges and opportunities associated with advancing Worldcoin, the goal itself needs to be defined more concretely.

Outlining a path to a permissionless protocol owned and governed by all of humanity

Advancing Decentralization

Tanguy Jeanneau, Wiktor Łazarski and Christian Brendel

Worldcoin requires a system that can accurately verify one's uniqueness among billions of users. In this article, we will explain how our biometric pipeline processes iris images to enable uniqueness verification on a large scale.

High Confidence Visual Recognition of Persons by a Test of Statistical Independence

Iris Feature Extraction with 2D Gabor Wavelets

Two-headed eye-segmentation approach for biometric identification

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Biometric Performance at a Billion People Scale

Opening the Orb: A look inside Worldcoin's biometric imaging device

Iris recognition inference system

Yi Chen, Tanguy Jeanneau and Christian Brendel

In this blog post, we discuss the traditional iris feature extraction method using Gabor filtering and why it works for iris texture.

Personal identification based on iris texture analysis

Emergence of simple-cell receptive field properties by learning a sparse code for natural images

Relations between the statistics of natural images and the response properties of cortical cells

Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognition

Iris feature extraction with 2D Gabor wavelets

A path to an open and permissionless identity protocol.

The Worldcoin project is initiating an open and permissionless identity protocol called World ID. It empowers individuals to verify their humanness online while maintaining their anonymity through zero-knowledge proofs. Advancements in AI make it difficult to distinguish between AI and humans on the internet, highlighting a need for authentic human recognition and verification. To help address this, individuals can receive a future-proof unique human credential through a secure biometric device in a privacy-preserving manner. Importantly, this enables a path to AI-funded non-state UBI and the equitable global distribution of digital currencies. The project's early contributors have developed initial versions of a hardware device, a mobile client, and a deployment mechanism—all of which will gradually become decentralized. World ID will ultimately enable the protocol to be governed by the people, ensuring that the protocol benefits everyone.

"participants in the study could only distinguish between human or AI text with 50-52% accuracy, about the same random chance as a coin flip."; https://www.pnas.org/doi/10.1073/pnas.2208839120

https://cyberlaw.stanford.edu/sites/default/files/FilteringOutTheBotsUnique2017NetNeutralityComments1024Update.pdf

Facial geometry mapping and audio style transfer facilitate digital impersonation via audio and video deep fakes. Notably, in 2022, Vitali Klitschko, the mayor of Kyiv, was impersonated by a deep fake. The attacker managed to conduct video conferences with several mayors of European capitals for up to 15 minutes. Some of the attacks were only uncovered days after the call. 

Democratic voting (one person one vote), quadratic voting, square root voting or any other weighting that requires the notion of a unique person see https://vitalik.ca/general/2021/08/16/voting3.html. Note that this is unlikely to replace the need to nevertheless prove relationships for certain applications.

Note that this doesn’t prevent users from creating a limited number of alternative accounts. Any platform could still allow several, but limited amounts of accounts to be created.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4105763

Note that the FPR (false positive rate of 1:N comparison against everyone who is enrolled) which can be approximated as N*FMR (false match rate for each individual 1:1 comparison) increases with the number of enrolled individuals. Therefore a false match rate of far beyond one in one billion is required to get to a global scale.

https://www.robots.ox.ac.uk/~az/lectures/est/iris.pdf

Although minor aging effects can be observed, they are negligible and considerably less significant compared to the variability within the image capture process (source). Employing optimized hardware and software can improve image capture consistency.

Humanness
in the Age of AI

Chris Brendel and other members of the Tools for Humanity Team

In this article, we show that iris recognition technology is capable of distinguishing individuals on a billion person scale. We discuss different operating modes and evaluate the expected failure rates as the user base grows.

Biometric performance at a billion person scale

Zero-Knowledge machine learning (ZKML) is a field of research and development that has been making waves in cryptography circles recently. But what is it and why is it useful? First, let's break down the term into its two constituents and explain what they are.

Zero-knowledge machine learning (ZKML) is a field of research and development that has been making waves in cryptography circles recently. But what is it and why is it useful? First, let's break down the term into its two constituents and explain what they are.

An introduction to zero-knowledge machine learning (ZKML)

After years of R&D, we’re opening up the Orb to explain how it works and releasing corresponding hardware engineering files.

Explanatory Note: Tools for Humanity (TFH) led the initial research and development of the Worldcoin protocol, including the Orb. This year, prior to the launch of the decentralized network, the non-profit Worldcoin Foundation is taking over responsibility for facilitating participation in, and the continued development of, the protocol. The Worldcoin Foundation will continue to support and grow the Worldcoin community until it becomes self-sufficient, while TFH will support the Foundation, including by manufacturing and shipping Orbs. Currently in beta, Worldcoin expects to launch in the first half of 2023.

Opening the Orb: 
A look inside Worldcoin’s biometric imaging device

This content is not available in your region

The thinking, ideas, and technology behind a more human economic system.

The Worldcoin Blog