Controlling Over-generalization and its Effect on Adversarial Examples Detection and Generation

ICLR 2019 Mahdieh AbbasiArezoo RajabiAzadeh Sadat MozafariRakesh B. BobbaChristian Gagné

Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.