Search Results for author:
Found 3 papers, 0 papers with code
Diffence: Fencing Membership Privacy With Diffusion Models
A unique feature of our defense is that it works on input samples only, without modifying the training or inference phase of the target model.
Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection
Experimental results show that the contribution of image transformations to adversarial detection is significantly different, the combination of them can significantly improve the generic detection ability against state-of-the-art adversarial attacks.
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features
In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image.
