Now showing items 1-4 of 4

    • Adversarial Patches Exploiting Contextual Reasoning in Object Detection 

      Saha, Aniruddha; Subramanya, Akshayvarun; Patil, Koninika (2019-12-21)
      The utilization of spatial context to improve accuracy in most fast object detection algorithms is well known. The detectors increase inference speed by doing a single forward pass per image which means they implicitly use ...
    • Hidden Trigger Backdoor Attacks 

      Saha, Aniruddha; Subramanya, Akshayvarun; Pirsiavash, Hamed (2019-12-21)
      With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial ...
    • Role of Spatial Context in Adversarial Robustness for Object Detection 

      Saha, Aniruddha; Subramanya, Akshayvarun; Patil, Koninika; Pirsiavash, Hamed
      The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use ...
    • Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs 

      Kolouri, Soheil; Saha, Aniruddha; Pirsiavash, Hamed; Hoffmann, Heiko
      The unprecedented success of deep neural networks in many applications has made these networks a prime target for adversarial exploitation. In this paper, we introduce a benchmark technique for detecting backdoor attacks ...