Developing the next generation of intelligent systems for missions characterized by uncertain, dynamic, and adversarial environments
Scientists and engineers in APL’s Intelligent Systems Center (ISC) work to enable confidence in intelligent systems for critical national security applications through research in uncertainty-aware risk sensitivity, safe and trustworthy artificial intelligence (AI), and testing and evaluation of emerging AI technologies. Our work involves close collaboration with experts and researchers from the .
ISC researchers address challenges in identifying, characterizing, and mitigating risks toward achieving safe deployment of AI in complex and challenging real-world settings. Research efforts address AI vulnerabilities across a range of threat models and operating conditions with the development of novel methods for dataset and model bias detection/mitigation, Trojan detection and removal, and adversarial and natural robustness evaluation.
