Research from Iowa State: an LLVM static analysis framework for a safety-critical library, and an evaluation harness for adversarial AI sponsored by Lockheed Martin.
Querying Program Analysis: An LLVM-based static analysis framework that maps control flow and audits security paths in LodePNG, answering queries instantly from the command line.
Adversarial Gameplay: An end-to-end evaluation harness that turns a black-box reinforcement-learning adversary into a system you can measure, compare, and explain.