WASHINGTON – U.S. intelligence experts are asking industry to develop to develop smart radio techniques that automatically detect and characterize suspicious signals and other RF anomalies in complex RF environments.
Officials of the Intelligence Advanced Research Projects Agency (IARPA) contracting office in Washington have released a broad agency announcement (IARPA-BAA-20-03) for the Securing Compartmented Information with Smart Radio Systems (SCISRS) program.
U.S. intelligence and military experts require information and data that is generated, stored, used, transmitted, and received in secure facilities and “in the wild,” IARPA officials say. Vigilance is necessary concerning the security of this kind of data regardless of where the data are being used.
The U.S. government has made significant investments in infrastructure to provide high confidence in data security in facilities under the control of the data owner, yet in environments where there is potentially much less control, data security becomes more challenging, IARPA officials explain.
One possible indicator of attempted data breach is unexpected RF transmissions. The goal of the SCISRS program is to develop smart radio techniques to detect and characterize these suspicious signals and other RF anomalies automatically in complex RF environments.
These anomalies can be LPI signals, altered or mimicked signals, abnormal, or unintended emanations. IARPA experts are looking for solutions that are scalable, computationally efficient, and adaptable to a range of radio hardware.
Devising a solution involved RF signal processing won't be easy, IARPA experts warn. RF frequencies of interest may range over several orders of magnitude and the data collection rates may approach terabytes per second -- about 1 million times higher than the data rate for high-definition video.
Leveraging technological advances in software defined radios (SDRs) and computational methods may help solve these problems. Laptop computers and tablet-sized software-defined radios today can handle RF signal processing that used to require a closet full of radio equipment. Wideband A/D converters, meanwhile, can convert a wide swath of the spectrum efficiently into a large effective number of bits (ENoB) with precise linearity and low noise.
In addition machine learning image recognition algorithms have become so efficient they can match video rates even with modest data processing. Moreover, the increasing ability of high-performance computing to accommodate the demands of machine learning techniques and digital signal processing may offer the potential to match 5G RF data rates.
The SCISRS program seeks to use off-the-shelf technologies for a wide variety of RF collection hardware that can detect and characterize various kinds of signals in environments cluttered with noise and interference.
Contractors chosen for the SCISRS program must be able to develop detection and characterization systems that work with a different architecture to be specified in each phase of the program.
IARPA will establish two test beds of RF emitters to handle anomalous signals. Contractors will install standardized collection hardware and provide an application programming interface (API) to control the hardware and format raw data for analysis.
Contractors must be able to demonstrate how they command and control the hardware for automatic detection and characterization of ambient signals.
The SCISRS program will have three phases, in which the level of difficulty and variety of anomalies will increase. The first phase focuses on RF baseline characterization and detection and characterization of LPI anomalies. The second phases focuses on altered and mimicked signal anomalies, and the third phase will focus on unintended emissions.
Companies interested should upload proposals no later than 13 Nov. 2020 to the IARPA Distribution and Evaluation System (IDEAS) online at https://iarpa-ideas.gov.
Email questions or concerns to IARPA at [email protected]. More information is online at https://beta.sam.gov/opp/f2e9128015684101b2021e04d37516c7/view.