Researcher profile
Jan Hendrik Metzen
2 papers in the PaperMetrix corpus
Publications
Papers by this author
-
Interpreting Adversarial Examples with Attributes
2019 · arXiv (Cornell University)
Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We …
-
Meta Adversarial Training against Universal Patches
2021 · arXiv (Cornell University)
Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversarial artifacts in the physical world that indirectly cause the …