Objective Metrics and Gradient Descent Algorithms for Adversarial Examples in Machine Learning

@inproceedings{Jang2017ObjectiveMA,
  title={Objective Metrics and Gradient Descent Algorithms for Adversarial Examples in Machine Learning},
  author={Uyeong Jang and Xi Wu and Somesh Jha},
  booktitle={ACSAC 2017},
  year={2017}
}
Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms are being used in diverse domains where security is a concern, such as, automotive systems, finance, health-care, computer vision, speech recognition, natural-language processing, and malware detection. Of particular concern is use of ML in cyberphysical systems, such as driver-less cars and aviation, where the presence of an adversary can cause serious consequences. In this paper we focus on attacks caused… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

Adversarial Robustness Toolbox v0.2.2

VIEW 10 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Task-specific Deep LDA pruning of neural networks.

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-5 OF 5 REFERENCES

Histograms of oriented gradients for human detection

  • Navneet Dalal, Bill Triggs
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 21 EXCERPTS
HIGHLY INFLUENTIAL

DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks

VIEW 21 EXCERPTS
HIGHLY INFLUENTIAL

Explaining and Harnessing Adversarial Examples

VIEW 17 EXCERPTS
HIGHLY INFLUENTIAL

Towards Evaluating the Robustness of Neural Networks

VIEW 1 EXCERPT
HIGHLY INFLUENTIAL

A Computational Approach to Edge Detection

  • John F. Canny
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1986
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL