Polygraph+

Problem Statement 

The Department of Defense (DoD) relies on credibility assessments (CAs) to vet new personnel during onboarding, evaluate existing DoD personnel for access to special or classified information, assist in determining source credibility, and interview subjects in criminal investigations. The DoD’s current CA standard requires trained evaluators to manually prepare, gather, and analyze data from polygraphs. Due to the manual efforts required under current CA protocols, the DoD sees room for improvement, optimization, and automation.

Desired Capabilities

The DoD seeks commercial solutions to optimize CA through a blend of user experience and automation upgrades. A minimum viable product should include a configurable system with new sensing tools, automated scoring, and usable interfaces that exceeds performance achieved by current capabilities and reduces the potential for human error and bias.

Prototyping will involve parallel lines of effort (LOEs); these LOEs may be executed by a single vendor bringing a comprehensive solution or by multiple vendors working in a teaming arrangement and demonstrating interoperability. Companies are also welcome to present their own teaming arrangements in their solution briefs. Vendors should be specific in their solution briefs if they intend to provide solutions for one or multiple LOEs. If applicable, vendors should explain how they will comply with human subject research requirements.  

LOE 1: Non-invasive physiological or behavioral sensing for objective CA measurement.

• A successful solution will measure physiological and behavioral signals with non-contact sensors that are validated against current CA measures.
• Sensing capabilities should follow healthcare industry standards.  
• Remote, “nearable,” and/or off-body assessments are preferred (e.g., visual perception sensing using high definition, depth, or thermal cameras; optical sensing; etc)
• Technologies that are robust across a range of physical environments are a plus.
• Example signals include, but are not limited to, respiration, heart rate, blood pressure, electrodermal activity, pupil diameter, and ocular movements. Desired solution should be able to accommodate next-generation signals.

LOE 2: Tools to automate data fusion and CA scoring, configurable for current and new data inputs.

• A successful solution will provide an automated scoring option in lieu of CA scoring performed by humans. It should be possible to validate this automated option against current polygraph standards.
• Scoring solutions should be capable of fusing and scoring current data physiological and behavioral signals (e.g., respiration, heart rate, electrodermal activity, ocular characteristics, etc).
• Automated CA scoring solutions should be able to accept and replicate scoring processes with new data signals, such as those collected via non-contact sensors in LOE 1.
• Requisite preprocessing tools to ingest, combine, and synchronize data inputs from multiple sensor sources are desired.
• Analytic tools with forward-compatibility to incorporate new sensor inputs are a plus.
• Feature extraction and classification models capable of discovering new CA measures are a plus.

LOE 3: Usable, intuitive tools to aid evaluator decision making.

• A successful solution will deliver CA scoring information through an interface that supports the adjudication process in real-time. 
• A CA dashboard should integrate with LOEs 1 and 2 to display relevant sensor and CA scoring information. 
• The UI features should remain configurable to accept new inputs, work in diverse contexts, and meet different end user preferences.

All LOEs should include accessible training tools to ease adoption into existing training pipelines.

Outside of these core LOE’s, the DoD is also interested in solutions capable of applying natural language processing tools to CA.

Additional Information

Prototype development will be accomplished across a phased approach. 

Phase 1 will involve a Benchmark of CA scoring and sensing technologies to include computational testing and usability testing. 

Phase 2 will involve in-lab validation and iterative development cycles based on feedback from live testing. The intent of the lab validation and live testing is to gather data for comparison against current polygraph results. Thus, preferential consideration will be given to solutions that have been built and deployed for similar CA problem sets. Vendors must demonstrate the ability to deliver mature solutions on a compressed timeline. Prototypes should initially focus on CA to vet individuals in controlled interview contexts, but also should be modular to allow for applications to field and operational contexts in the future.

Phase 3 will involve network accreditation to ensure full functionality and deployment on DoD systems. Existing authority to operate (ATO) and/or certification as a system of record are a plus. Vendors must possess or be able to obtain Federal Risk and Authorization Management Program (FedRAMP) Moderate accreditation along with Defense Information Systems Agency (DISA) Impact Level (IL)-4 provisional authority (PA) or offer solutions that are compatible with services that have already attained an ATO and are DISA IL-4-compliant. Final product(s) must be compliant with FedRAMP Moderate Impact Risk Level. 

Vendors possessing or able to obtain a U.S. National Security Facility Clearance are a plus.  

DIU requires that respondents to this Area of Interest (AOI) acknowledge their knowledge of and familiarity with the Department of Defense (DoD) Ethical Principles for Artificial Intelligence and the DIU Responsible AI (RAI) Guidelines that implement them. Vendors responding to this AOI will be expected to align their work with the Responsible AI Guidelines attached. Inability to align with these Guidelines may affect selection for the prototype.

Submission Guidance

Awarding Instrument: Any award(s) resulting from this announcement will be awarded as an Other Transaction under the authority of 10 U.S.C. 4022 (formerly 10 U.S.C. 2371b) and Commercial Solutions Opening (CSO) HQ0845-20-S-C0001 posted to Beta.SAM.Gov website on 23 March 2020.

Follow-on Production: Companies are advised that any Prototype Other Transaction (OT) agreement awarded in response to this solicitation may result in the direct award of a follow-on production contract or agreement without the use of further competitive procedures. Follow-on production activities may result from successful prototype completion.

The follow-on production contract or agreement will be available for use by one or more organizations within the Department of Defense. As a result, the magnitude of the follow-on production contract or agreement could be significantly larger than that of the Prototype OT agreement. All Prototype OT agreements will include the following statement relative to the potential for follow-on production: “In accordance with 10 U.S.C. § 4022(f), and upon a determination that the prototype project for this transaction has successfully been completed, this competitively awarded Prototype OT agreement may result in the award of a follow-on production contract or transaction without the use of competitive procedures.”

• Companies without a Commercial and Government Entity (CAGE) code will be required to register in the Systems for Award Management (SAM) if selected. The DoD recommends that prospective companies begin this process as early as possible.
• Any resulting agreement from this AOI will include language requiring your company to confirm compliance with Section 889 of the John S. McCain National Defense Authorization Act for Fiscal Year 2019 (Pub. L. 115-232). If you are unable to confirm compliance with the referenced law, the government is unable to enter into an agreement with your company
• Any small business or non-traditional vendor is encouraged to apply. Vendors not meeting those conditions can qualify under the following conditions:
  • Teams with at least one non-traditional defense contractor or non-profit research institution with significant participation in the prototype project.
  • At least one-third of total costs must be paid by parties to the OT other than the government.
  • Non-Traditional Defense Contractor definition: An entity that is not currently performing and has not performed, for at least the one-year period preceding the solicitation of sources by DoD for the procurement or transaction, any contract or subcontract for the DoD that is subject to full coverage under the cost accounting standards prescribed pursuant to section 1502 of title 41 and the regulations implementing such section (see 10 U.S.C 2302(9)).

Solution Brief Requirements

Solution Briefs should not exceed five (5) written pages using 12-point font or, alternatively, Solution Briefs may take the form of briefing slides which should not exceed fifteen (15). Please note that there is a 10MB file upload limit.

Suggested Content:

• Title Page (does not count against the page limit): Company Name, Title, Date, Point of Contact Name, E-Mail Address, Phone, and Address. Specifically identify the solicitation for which the Solution Brief is submitted. Indicate the LOE(s) being addressed.
• Executive Summary (one page): Provide an executive summary of the solution.
• Technology Concept: Describe the unique aspects of your technology and the proposed work as it relates to the solicitation. Describe the data, including data elements, age and volume. Identify whether the effort includes a pilot or demonstration of existing technology (identified as commercially ready and viable technology), or the adaptation of technology for a potential defense application. If adaptation is proposed, identify a suggested path to mature the technology. Provide architecture drawings of how capability components will interact. Identify aspects which may be considered proprietary.
• Company Information: Provide a brief overview of the company, including a summary of gross sales/revenue and investors funding rounds (if applicable). Provide a summary of product history, roadmap, and go-to-market strategy.
• Including an existing customer list and/or customer case studies is encouraged.