SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
Quick summary
arXiv:1906.07927v4 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently, most such adversarial examples try to guarantee "subtle perturbation" by limiting the $L_p$ norm of the perturbation. In this paper, we aim to explore the impact of semantic manipulation on DNNs predictions by manipulating the semantic attributes o
Key takeaways
- arXiv:1906.07927v4 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power.
- However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipulated instances targeting to mislead DNNs to make incorrect predictions.
- Currently, most such adversarial examples try to guarantee "subtle perturbation" by limiting the $L_p$ norm of the perturbation.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments