The Limitations of Deep Learning in Adversarial Settings

24 Nov 2015Nicolas PapernotPatrick McDanielSomesh JhaMatt FredriksonZ. Berkay CelikAnanthram Swami

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify... (read more)

PDF Abstract

Evaluation 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.