Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

2020 
Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite significant research on developing DNN attack and defense techniques, people still lack an understanding of how such attacks penetrate a model's internals. We present Bluff, an interactive system for visualizing, characterizing, and deciphering adversarial attacks on vision-based neural networks. Bluff allows people to flexibly visualize and compare the activation pathways for benign and attacked images, revealing mechanisms that adversarial attacks employ to inflict harm on a model. Bluff is open-sourced and runs in modern web browsers.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    43
    References
    4
    Citations
    NaN
    KQI
    []