Beyond Explainability: Leveraging Interpretability for Improved Adversarial Learning

April 21, 2019 ยท Declared Dead ยท ๐Ÿ› CVPR Workshops

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Devinder Kumar, Ibrahim Ben-Daya, Kanav Vats, Jeffery Feng, Graham Taylor and, Alexander Wong arXiv ID 1904.09633 Category cs.LG: Machine Learning Cross-listed cs.CR, cs.CV, stat.ML Citations 1 Venue CVPR Workshops Last Checked 4 months ago
Abstract
In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability. In particular, this study puts forward a novel strategy for leveraging gradient-based interpretability in the realm of adversarial examples, where we use insights gained to aid adversarial learning. More specifically, we introduce the concept of spatially constrained one-pixel adversarial perturbations, where we guide the learning of such adversarial perturbations towards more susceptible areas identified via gradient-based interpretability. Experimental results using different benchmark datasets show that such a spatially constrained one-pixel adversarial perturbation strategy can noticeably improve the speed of convergence as well as produce successful attacks that were also visually difficult to perceive, thus illustrating an effective use of interpretability methods for tasks outside of the purpose of purely explainability.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted