Search Results for author:
Found 5 papers, 1 papers with code
Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
Graph representation learning has long been an important yet challenging task for various real-world applications.
Decoder-free Robustness Disentanglement without (Additional) Supervision
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features.
Structure Matters: Towards Generating Transferable Adversarial Images
In this paper, we propose the novel concepts of structure patterns and structure-aware perturbations that relax the small perturbation constraint while still keeping images natural.
DO-AutoEncoder: Learning and Intervening Bivariate Causal Mechanisms in Images
Our experiments demonstrate our method is able to correctly identify the bivariate causal relationship between concepts in images and the representation learned enables a do-calculus manipulation to images, which generates artificial images that might possibly break the physical law depending on where we intervene the causal system.
Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
A common requirement in all these works is that the malicious perturbations should be small enough (measured by an L_p norm for some p) so that they are imperceptible to humans.
