← Search

Insik Shin

1 accepted papers

2022

Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future

IJCAI 2022poster

Recurrent models are frequently being used in online tasks such as autonomous driving, and a comprehensive study of their vulnerability is called for. Existing research is limited in generality only addressing application-specific vulnerability or making implausible assumptions such as the knowledge…