Request for Information: Techniques and Tools for Vulnerability Assessment of AI-enabled Systems
| Location: | Federal |
|---|---|
| Posted: | Jan 17, 2025 |
| Due: | Feb 28, 2025 |
| Agency: | DEPT OF DEFENSE |
| Type of Government: | Federal |
| Category: |
|
| Solicitation No: | DARPA-SN-25-28 |
| Publication URL: | To access bid details, please log in. |
Follow
Active
Contract Opportunity
Notice ID
DARPA-SN-25-28
Related Notice
Department/Ind. Agency
DEPT OF DEFENSE
Sub-tier
DEFENSE ADVANCED RESEARCH PROJECTS AGENCY (DARPA)
Office
DEF ADVANCED RESEARCH PROJECTS AGCY
General Information
Classification
Description
Contact Information
History
- Contract Opportunity Type: Special Notice (Original)
- Original Published Date: Jan 17, 2025 02:11 pm EST
- Original Response Date: Feb 28, 2025 05:00 pm EST
- Inactive Policy: Manual
- Original Inactive Date: Mar 01, 2025
-
Initiative:
- None
- Original Set Aside:
- Product Service Code: AC12 - NATIONAL DEFENSE R&D SERVICES; DEPARTMENT OF DEFENSE - MILITARY; APPLIED RESEARCH
-
NAICS Code:
-
Place of Performance:
The Defense Advanced Research Projects Agency (DARPA) Information Innovation Office (I2O) seeks information from industry developers and academic institutions regarding current and emerging techniques and tools for the operational assessment of potential vulnerabilities in DoD relevant artificial intelligence (AI)-enabled systems.
We seek techniques and tools that: 1) consider a spectrum of relevant adversarial access threat models (white box, grey box, black box, hidden box), 2) consider not just the AI model, but also vulnerabilities presented by the entire AI-enabled system development and deployment pipeline, and 3) consider the platform specific quirks in operationally assessing vulnerabilities including environmental conditions, multi-modal sensor ingest, and system purpose.
Responses to this RFI will be used to assess the current state of the art and to identify core gaps that will need to be addressed by a future program in AI vulnerability assessment.
We seek techniques and tools that: 1) consider a spectrum of relevant adversarial access threat models (white box, grey box, black box, hidden box), 2) consider not just the AI model, but also vulnerabilities presented by the entire AI-enabled system development and deployment pipeline, and 3) consider the platform specific quirks in operationally assessing vulnerabilities including environmental conditions, multi-modal sensor ingest, and system purpose.
Responses to this RFI will be used to assess the current state of the art and to identify core gaps that will need to be addressed by a future program in AI vulnerability assessment.
Attachments/Links
Contracting Office Address
- 675 NORTH RANDOLPH STREET
- ARLINGTON , VA 222032114
- USA
Primary Point of Contact
- BAA Coordinator
- DARPA-SN-25-28@darpa.mil
Secondary Point of Contact
- Jan 17, 2025 02:11 pm ESTSpecial Notice (Original)
Daily notification on new contract opportunities
With GovernmentContracts, you can:
- Find more opportunities and win more business
- Receive daily alerts for all new bid opportunities
- Get contract opportunities matched to your business
See also
...program vulnerability from successful adversary collection and exploitation of critical information...
DEPT OF DEFENSE
Bid Due: 10/30/2029
...program vulnerability from successful adversary collection and exploitation of critical information...
DEPT OF DEFENSE
Bid Due: 10/30/2029
...program vulnerability from successful adversary collection and exploitation of critical information...
DEPT OF DEFENSE
Bid Due: 10/30/2029
...program vulnerability from successful adversary collection and exploitation of critical information...
DEPT OF DEFENSE
Bid Due: 10/30/2029
* Disclaimer: Information regarding bids, requests for proposals (RFPs), or requests for qualifications (RFQs) is provided on this website only for convenience and does not constitute official public notice. Persons wishing to respond to or inquire about bids, RFPs, or RFQs should contact the appropriate government department.