أرسل هذا في رسالة قصيرة: Investigating the causes of the vulnerability of CNNs to adversarial perturbations: learning objective, model components, and learned representations

  _____     _____    __   __   __   __    _____   
 / ____||  |  ___||  \ \\/ //  \ \\/ //  /  ___|| 
/ //---`'  | ||__     \   //    \ ` //  | // __   
\ \\___    | ||__     / . \\     | ||   | \\_\ || 
 \_____||  |_____||  /_//\_\\    |_||    \____//  
  `----`   `-----`   `-`  --`    `-`'     `---`