BIO
Securing agentic AI systems with self-improving red-teaming and guardrail agents.
Maksym Andriushchenko
@maksym_andr
Principal investigator @ELLISInst_Tue & @MPI_IS, mentor @MATSprogram, PhD from @EPFL, past works: AgentHarm, HalluHard, Claudini, PostTrainBench, InferenceBench
