Safe Paths is an MIT-led, free, open source technology that enables jurisdictions and individuals to maximize privacy, while also maximizing the effectiveness of contact tracing in the case of a positive diagnosis. The Safe Paths platform, currently in beta, comprises both a smartphone application, PrivateKit, and a web application, Safe Places. The PrivateKit app will enable users to match the personal diary of location data on their smartphones with anonymized, redacted, and blurred location history of infected patients. The digital contact tracing uses overlapped GPS and Bluetooth trails that allow an individual to check if they have crossed paths with someone who was later diagnosed positive for the virus. Through Safe Places, public health officials are equipped to redact location trails of diagnosed carriers and thus broadcast location information with privacy protection for both diagnosed patients and for local businesses.

Context 
Fast containment is key to halting an epidemic outbreak. But with the long incubation period of a virus like COVID-19, it is extremely difficult to identify individuals w… View full description

Safe Paths is an MIT-led, free, open source technology that enables jurisdictions and individuals to maximize privacy, while also maximizing the effectiveness of contact tracing in the case of a positive diagnosis. The Safe Paths platform, currently in beta, comprises both a smartphone application, PrivateKit, and a web application, Safe Places. The PrivateKit app will enable users to match the personal diary of location data on their smartphones with anonymized, redacted, and blurred location history of infected patients. The digital contact tracing uses overlapped GPS and Bluetooth trails that allow an individual to check if they have crossed paths with someone who was later diagnosed positive for the virus. Through Safe Places, public health officials are equipped to redact location trails of diagnosed carriers and thus broadcast location information with privacy protection for both diagnosed patients and for local businesses.

Context 
Fast containment is key to halting an epidemic outbreak. But with the long incubation period of a virus like COVID-19, it is extremely difficult to identify individuals who may have been in contact with carriers of the virus and are thus at risk of contagion. Across the globe, the use of smartphones has been tested to track location and solve this problem, raising concerns about mass surveillance.  However, with our privacy-first method, the user remains in control of their data—providing a fundamentally different approach to app-based epidemic analytics.

Resilience requires citizens and organizations to self-organize so that they can predict and respond to challenges (e.g., climate change) and disruptions (e.g., COVID-19). Such orchestration would be easy if everyone involved shared data about their past activities and future intentions openly, and responded to scientific evidence in ways that supported long term resilience, fairness, inclusiveness and accountability. This is, however, is challenging due to the need to maintain privacy, consent, trade secrets and compatible incentives.

The current epidemic highlights this challenge. A "big brother" system in some countries has made a big difference in public health intervention via contact tracing, quarantine adherence verification, health verification, as well as tools for health officials such as spread analysis, resource allocation and incentive methods.

Unfortunately, network analysis of social activities leads to a surveillance state. Thus, there are several big challenges to capture, analyze and act in a closed loop: (i) population scale understanding of a fast or slow moving threat without coercing an individual to reveal anything identifiable about themselves, (ii) analyze and providing precise guidance to an individual without the orchestration system knowing to who and what message is delivered and (iii) incentivize and verify the action while maintaining a sense of agency and privacy for the individual.

These seemingly impossible problems can now be addressed thanks to (i) deep penetration of smartphones and IoT which can act to capture, compute, disseminate and act on information. (ii) the data sources associated with these devices (iii) practical and scalable privacy preserving algorithms and (iv) incentive mechanisms for networks of people and agents which act to guide individuals to support not only themselves but the society as a whole.

Transparent, accountable, and inclusive ecosystems that can simultaneously address the privacy and utility of data in building resilient societal systems are key to humanity's future.
In the short run, digital tracing and infection spread analysis, monitoring of logistics and service chains, and simulation to help policy makers will help the current public health challenges. In the medium term, such systems will be critical in restarting socio-economic activities and get the society on track to more perm

For upcoming version releases, Private Kit: Safe Paths will deploy the following capabilities: 

  • V1 - Log location history
  • V2 - Match personal location history with infected patient anonymous redacted trace files provided by public health officials
  • V3 - Match personal  location history with encrypted anonymous redacted infected patient trace files provided by city officials

As noted, Private Kit: Safe Paths works in conjunction with the MIT-developed GIS web app, Safe Places

Safe Places will be used by public health officials to:

  1. Collect time-stamped location data from one of the three sources, Private Kit: Safe Paths, Google location history, and patient interviews
  2. Produce partially obscured trace files that meet jurisdiction legal requirements for anonymity that can be posted openly on the web and utilized for contact tracing in Private Kit: Safe Paths

By enabling contact tracing, Private Kit: Safe Paths will help to reduce panic and "flatten the curve" of Coronavirus spread by enabling those who have been exposed and are showing symptoms to make more informed decisions on when to seek testing and self-quarantine—without losing individual privacy and while reducing the fear unknown exposure.

The Team

Led by Ramesh Raskar, the Safe Paths project is a multi-faculty, cross-MIT effort, with input and expertise from institutes including Harvard University, Stanford University, and SUNY Buffalo; clinical input from Mayo Clinic and Massachusetts General Hospital; and mentors from the World Health Organization, the US Department of Health and Human Services, and the Graduate Institute of International and Development Studies. 

A number of leaders and personnel from the global company EY are volunteering their time across many disciplines, including strategy and inclusion on the core initiative leadership team. Numerous additional companies are also participating in this way, including TripleBlind, Public Consulting Group, and Earned Media Consultants 

Experts from government agencies and academic institutes in Canada, Germany, India, Italy, the United Kingdom, and Vietnam are also helping to guide the platform’s development.