Project Lead: Dr. Bruce Draper
Sponsoring Organization: DARPA
Project Synopsis: Machine learning techniques are susceptible to adversarial deception at training time and when deployed. Humans also are susceptible to being deceived by falsified media and other information created with malicious intent. RED aims to develop techniques that automatically reverse-engineer and identify the toolchains behind attacks, such as multimedia falsification, adversarial ML attacks, or other information deception attacks, as well as develop and maintain scalable databases of attack toolchains.