Search Results for author:
Found 10 papers, 0 papers with code
STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness.
SSTA: Salient Spatially Transformed Attack
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.
DTA: Distribution Transform-based Attack for Query-Limited Scenario
In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials during an attack.
Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Hence, it provides a way to directly generate stego images from secret images without a cover image.
AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks.
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack
However, the distribution of these fake data lacks diversity and cannot detect the decision boundary of the target model well, resulting in the dissatisfactory simulation effect.
Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?
With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms.
Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networks
Inspired by this, we propose a novel model inversion attack method on HomoGNNs and HeteGNNs, namely HomoGMI and HeteGMI.
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models.
Improving robustness of softmax corss-entropy loss via inference information
Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.
