18 citations · 29 across the 10 of their papers we have counts for
13 papers
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
Hongbo Wang, AprilPyone MaungMaung, Isao Echizen
Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understanding but inherit toxic signals from weakl…
Image and Model Transformation with Secret Key for Vision Transformer
Hitoshi Kiya, Ryota Iijima, MaungMaung Aprilpyone +1
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained wit…
Privacy-Preserving Image Classification Using Isotropic Network
AprilPyone MaungMaung, Hitoshi Kiya
In this paper, we propose a privacy-preserving image classification method that uses encrypted images and an isotropic network such as the vision transformer. The proposed method a…
Adversarial Detector with Robust Classifier
Takayuki Osakabe, Maungmaung Aprilpyone, Sayaka Shiota +1
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper,…
Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models
Hiroki Ito, MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose an access control method that uses the spatially invariant permutation of feature maps with a secret key for protecting semantic segmentation models. Segm…
A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access
MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose a model protection method for convolutional neural networks (CNNs) with a secret key so that authorized users get a high classification accuracy, and unau…
Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access
Hiroki Ito, MaungMaung AprilPyone, Hitoshi Kiya
Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a…
Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key
MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in…
Transfer Learning-Based Model Protection With Secret Key
MaungMaung AprilPyone, Hitoshi Kiya
We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage o…
Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks
MaungMaung AprilPyone, Hitoshi Kiya
We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demo…
Block-wise Image Transformation with Secret Key for Adversarially Robust Defense
MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples fo…
Encryption Inspired Adversarial Defense for Visual Classification
MaungMaung AprilPyone, Hitoshi Kiya
Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the…
Adversarial Test on Learnable Image Encryption
MaungMaung AprilPyone, Warit Sirichotedumrong, Hitoshi Kiya
Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, exist…