DARPA-SN-25-39.pdf
PDF 207 KB Posted
- Attached to
- Future Program: Securing Artificial Intelligence for Battlefield Effective Robustness (SABER) Federal contract opportunity
- Solicitation number
- DARPA-SN-25-39
About this file
This Special Notice from DARPA's Information Innovation Office announces the forthcoming Securing Artificial Intelligence for Battlefield Effective Robustness (SABER) program. The program aims to build an AI red team capable of operationally assessing AI-enabled battlefield systems, particularly autonomous ground and aerial systems planned for deployment within 1-3 years.
The notice seeks potential performers who can assist with surveying, evaluating, developing, and employing state-of-the-art counter-AI techniques including physical (manufacturing/materials), adversarial AI (digital), cyber, and electronic warfare tools. DARPA also seeks an integration lead to create an interoperable operational AI red teaming toolkit for DoD and U.S. Government use. While this is not a formal solicitation or RFI and no submissions are being accepted, interested parties are directed to monitor https://sam.gov for the future solicitation. The program is led by I2O Program Manager LTC Nathaniel D. Bastian, PhD, and free resources are available through DARPAConnect at www.DARPAConnect.us.
View the file
On GovTribe
Work with this file on GovTribe
- Download the original file
- Contacts named in this file
- Similar government files
- Ask GovTribe AI about this file
Text version
Special Notice Information Innovation Office
Future Program: Securing Artificial Intelligence for Battlefield Effective Robustness (SABER)
DARPA-SN-25-39
January 29, 2025
PROGRAM ANNOUNCEMENT
The purpose of this Special Notice is to provide public notification of additional research areas of interest to the Defense Advanced Research Projects Agency (DARPA) Information Innovation Office (I2O), specifically for the forthcoming Securing Artificial Intelligence for Battlefield Effective Robustness (SABER) program by I2O Program Manager, LTC Nathaniel D. Bastian, PhD.
If released, the solicitation will be made available at https://sam.gov.
PROGRAM BACKGROUND AND OBJECTIVES
Given the latest advances in artificial intelligence (AI), the technology has reached a level of maturity, prompting a growing desire for these technologies to be integrated into Department of Defense (DoD) systems. AI may used to give battlefield advantage by helping improve the speed, quality, and accuracy of decision-making while enabling autonomy and assistive automation. Due to the statistical nature of machine learning, prior work has focused primarily on ensuring the robustness of AI-enabled systems at inference time due to natural degradations in performance caused by data distribution shifts, for example, from a highly dynamic deployment environment. However, as early as 2014, AI has been demonstrated as manipulable given adversary control of the input [1].1 Initial work has further confirmed the theoretical risks of data poisoning [2], physically constrained adversarial patches for evasion [3], and model stealing attacks [4]. These attacks are typically tested in simulated or physical environments with relatively pristine control compared to what might be expected on a battlefield. Today, there is no known reported ecosystem that operationally assesses deployed military AI-enabled systems for adversarial vulnerabilities, so the “theoretical” adversarial AI attacks have not been practically demonstrated in operational settings. Given this, the operational security risks of AI-enabled battlefield systems remain unknown. As such, SABER will build an exemplar AI red team equipped with the necessary counter-AI techniques, tools and technical competency to operationally assess AI-enabled battlefield systems, while establishing a sustainable model for an evergreen operational AI red teaming process. Our AI red team will be operationally assessing AI-enabled autonomous ground and aerial systems that could be deployed within the next 1-3 years. To assist the AI red team, the future solicitation will seek performers who can assist in surveying, evaluating, selecting, developing, and employing state-of-the-art physical (including manufacturing/materials), adversarial AI (including digital), cyber and electronic warfare techniques and tools, or other relevant vectors for enabling the operational assessment of AI-enabled system development and deployment pipelines [5]. Additionally, the forthcoming solicitation will seek a performer to serve as an integration lead, assisting in integrating the technologies into an interoperable operational AI red teaming toolkit to equip the AI red team and enable future AI red teams for the DoD and broader U.S. Government.
1 Citations:
1- https://arxiv.org/abs/1412.6572
2- https://arxiv.org/abs/1804.00792
3- https://arxiv.org/pdf/2104.06728
4- https://arxiv.org/abs/2411.10023
5- https://sam.gov/opp/041e8bd594c1450dbec14a6ca580fbed/view https://sam.gov/ https://arxiv.org/abs/1412.6572 https://arxiv.org/abs/1804.00792 https://arxiv.org/pdf/2104.06728 https://arxiv.org/abs/2411.10023 https://sam.gov/opp/041e8bd594c1450dbec14a6ca580fbed/view
DARPACONNECT
DARPAConnect offers free resources to potential performers to help them navigate DARPA, including “Understanding DARPA Award Vehicles and Solicitations,” “Making the Most of Proposers Days,” and “Tips for DARPA Proposal Success.” Join DARPAConnect at www.DARPAConnect.us to leverage on-demand learning and networking resources.
NOTE: This Special Notice does not constitute a formal solicitation for proposals. This notice is issued solely for information and program planning purposes and is not a Request for Information (RFI). Since this is not an RFI, no submissions against this notice will be accepted by DARPA. Interested parties to this notice are cautioned that nothing herein obligates DARPA to issue a solicitation.
NO CLASSIFED INFORMATION SHOULD BE INCLUDED IN ANY COMMUNICATIONS IN
RESPONSE TO THIS SPECIAL NOTICE.
http://www.darpaconnect.us/
File details come from the government source that posted it. Updated .