Geospatial-temporal pathogen tracing in zero knowledge
Techniques for geospatial-temporal pathogen tracing in zero knowledge include: generating, by a first user device, a first proximity token for contact tracing; receiving, by the first user device, a second proximity token from a second user device; generating, by the first user device, a hash based on the first proximity token and the second proximity token; generating, by the first user device using a prover function of a preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK), a cryptographic proof attesting that an individual associated with the first user device tested positive for a pathogen; transmitting, by the first user device, first publicly verifiable exposure data including at least the cryptographic proof and the hash to a public registry; and applying at least the first publicly verifiable exposure data and second publicly verifiable exposure data to a machine learning model, to obtain actionable intelligence associated with the pathogen.
1. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
generating, by a first user device, a first proximity token for contact tracing, wherein the first proximity token is generated according to a schedule and based on a random string associated with the first user device;
receiving, by the first user device, a second proximity token from a second user device, wherein the second proximity token is generated according to the schedule and based on a random string associated with the second user device;
sorting, by the first user device, the first proximity token and the second proximity token according to a sorting criteria used by both the first user device and the second user device;
generating, by the first user device, a first hash based on:
the first proximity token and the second proximity token; and
the sorting of the first proximity token and the second proximity token;
generating, by the first user device using a prover function of a preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK), a first cryptographic proof attesting that:
a first individual associated with the first user device was in a target proximity with a second individual associated with the second user device at a first time point; and
the first individual tested positive for a pathogen at a second time point within a threshold duration of the first time point;
transmitting, by the first user device, first publicly verifiable exposure data comprising at least the first cryptographic proof and the first hash to a public registry;
applying at least the first publicly verifiable exposure data, second publicly verifiable exposure data, and traffic data associated with movement of user devices within a geospatial region to a machine learning model, to obtain actionable intelligence associated with the pathogen;
generating a graph visualization corresponding to the traffic data; and
based at least on the actionable intelligence, determining one or more of:
a predicted future hotspot for the pathogen; and
a pathogen exposure risk of a user of the second user device.
2. The one or more non-transitory computer-readable media of claim 1 , wherein:
generating the first cryptographic proof is based on comparing a first randomness associated with the first hash with a second randomness associated with a second hash comprised in the second publicly verifiable exposure data; and
the machine learning model is a temporal self-attention network.
3. The one or more non-transitory computer-readable media of claim 2 , the operations further comprising:
generating a first regional graph based at least on the first publicly verifiable exposure data;
embedding the first regional graph as a first set of points in a first latent vector space;
generating a second regional graph based at least on the second publicly verifiable exposure data;
embedding the second regional graph as a second set of points in a second latent vector space; and
generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.
4. The one or more non-transitory computer-readable media of claim 3 , the first regional graph comprising a plurality of nodes representing respective locations in the geospatial region and a plurality of edges representing traffic flow between the respective locations.
5. The one or more non-transitory computer-readable media of claim 1 , the second publicly verifiable exposure data comprising a second cryptographic proof attesting that a second individual associated with the second user device had contact with a third individual associated with a third user device.
6. A system comprising:
at least one device including a hardware processor;
the system being configured to perform operations comprising:
generating, by a first user device, a first proximity token for contact tracing, wherein the first proximity token is generated according to a schedule and based on a random string associated with the first user device;
receiving, by the first user device, a second proximity token from a second user device, wherein the second proximity token is generated according to the schedule and based on a random string associated with the second user device;
sorting, by the first user device, the first proximity token and the second proximity token according to a sorting criteria used by both the first user device and the second user device;
generating, by the first user device, a first hash based on:
the first proximity token and the second proximity token; and
the sorting of the first proximity token and the second proximity token;
generating, by the first user device using a prover function of a preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK), a first cryptographic proof attesting that:
a first individual associated with the first user device was in a target proximity with a second individual associated with the second user device at a first time point; and
the first individual tested positive for a pathogen at a second time point within a threshold duration of the first time point;
transmitting, by the first user device, first publicly verifiable exposure data comprising at least the first cryptographic proof and the first hash to a public registry;
applying at least the first publicly verifiable exposure data, second publicly verifiable exposure data, and traffic data associated with movement of user devices within a geospatial region to a machine learning model, to obtain actionable intelligence associated with the pathogen;
generating a graph visualization corresponding to the traffic data; and
based at least on the actionable intelligence, determining one or more of:
a predicted future hotspot for the pathogen; and
a pathogen exposure risk of a user of the second user device.
7. The system of claim 6 , wherein:
generating the first cryptographic proof is based on comparing a first randomness associated with the first hash with a second randomness associated with a second hash comprised in the second publicly verifiable exposure data; and
the machine learning model is a temporal self-attention network.
8. The system of claim 7 , the operations further comprising:
generating a first regional graph based at least on the first publicly verifiable exposure data;
embedding the first regional graph as a first set of points in a first latent vector space;
generating a second regional graph based at least on the second publicly verifiable exposure data;
embedding the second regional graph as a second set of points in a second latent vector space; and
generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.
9. The system of claim 8 , the first regional graph comprising a plurality of nodes representing respective locations in the geospatial region and a plurality of edges representing traffic flow between the respective locations.
10. The system of claim 6 , the second publicly verifiable exposure data comprising a second cryptographic proof attesting that a second individual associated with the second user device had contact with a third individual associated with a third user device.
11. The system of claim 6 , the operations further comprising: generating, by the second user device, a second cryptographic proof attesting that:
the second individual associated with the second user device was in a target proximity with the first individual associated with the first user device at a third time point;
the first individual tested positive for the pathogen; and
the second individual associated with the second user device was in a target proximity with a third individual associated with a third user device at a third time point, wherein the third time point is greater than or equal to a sum of the first time point and an incubation period associated with the pathogen; and
transmitting, by the second user device, second publicly verifiable exposure data comprising at least the second cryptographic proof and a second hash associated with the second user device to the public registry.
12. A method comprising:
generating, by a first user device, a first proximity token for contact tracing, wherein the first proximity token is generated according to a schedule and based on a random string associated with the first user device;
receiving, by the first user device, a second proximity token from a second user device, wherein the second proximity token is generated according to the schedule and based on a random string associated with the second user device;
sorting, by the first user device, the first proximity token and the second proximity token according to a sorting criteria used by both the first user device and the second user device;
generating, by the first user device, a first hash based on:
the first proximity token and the second proximity token; and
the sorting of the first proximity token and the second proximity token;
generating, by the first user device using a prover function of a preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK), a first cryptographic proof attesting that:
a first individual associated with the first user device was in a target proximity with a second individual associated with the second user device at a first time point; and
the first individual tested positive for a pathogen at a second time point within a threshold duration of the first time point;
transmitting, by the first user device, first publicly verifiable exposure data comprising at least the first cryptographic proof and the first hash to a public registry;
applying at least the first publicly verifiable exposure data, and second publicly verifiable exposure data, and traffic data associated with movement of user devices within a geospatial region to a machine learning model, to obtain actionable intelligence associated with the pathogen;
generating a graph visualization corresponding to the traffic data; and
based at least on the actionable intelligence, determining one or more of:
a predicted future hotspot for the pathogen; and
a pathogen exposure risk of a user of the second user device.
13. The method of claim 12 , wherein:
generating the first cryptographic proof is based on comparing a first randomness associated with the first hash with a second randomness associated with a second hash comprised in the second publicly verifiable exposure data; and
the machine learning model is a temporal self-attention network.
14. The method of claim 13 , further comprising:
generating a first regional graph based at least on the first publicly verifiable exposure data;
embedding the first regional graph as a first set of points in a first latent vector space;
generating a second regional graph based at least on the second publicly verifiable exposure data;
embedding the second regional graph as a second set of points in a second latent vector space; and
generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.
15. The method of claim 14 , the first regional graph comprising a plurality of nodes representing respective locations in the geospatial region and a plurality of edges representing traffic flow between the respective locations.
16. The method of claim 12 , the second publicly verifiable exposure data comprising a second cryptographic proof attesting that a second individual associated with the second user device had contact with a third individual associated with a third user device.
17. The method of claim 12 , further comprising: generating, by the second user device, a second cryptographic proof attesting that:
the second individual associated with the second user device was in a target proximity with the first individual associated with the first user device at a third time point;
the first individual tested positive for the pathogen; and
the second individual associated with the second user device was in a target proximity with a third individual associated with a third user device at a third time point, wherein the third time point is greater than or equal to a sum of the first time point and an incubation period associated with the pathogen; and
transmitting, by the second user device, second publicly verifiable exposure data comprising at least the second cryptographic proof and a second hash associated with the second user device to the public registry.