Adversarial Markov Games: On Adaptive Decision-Based Attacks and Defenses. (arXiv:2312.13435v1 [cs.AI])

Despite considerable efforts on making them robust, real-world ML-based
systems remain vulnerable to decision based attacks, as definitive proofs of
their operational robustness have so far proven intractable. The canonical
approach in robustness evaluation calls for adaptive attacks, that is with
complete knowledge of the defense and tailored to bypass it. In this study, we
introduce a more expansive notion of being adaptive and show how attacks but
also defenses can benefit by it and by learning from each other …

adversarial attacks canonical decision defense defenses evaluation far games knowledge making operational real robustness systems vulnerable world