Maungmaung Aprilpyone
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maungmaung Aprilpyone has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hitoshi Kiya
Tokyo Metropolitan University rd 6-6 Asahigaoka Hino Tokyo Japan
9 shared publications - Isao Echizen
The University of Tokyo Japan
3 shared publications - Yuma Kinoshita
Department of Computer Science, Tokyo Metropolitan University, Tokyo, Japan
2 shared publications - Hiroki Ito
Department of Computer Science, Tokyo Metropolitan University, Tokyo, Japan
1 shared publication - Hiroki Ito1 shared publication
- Koichi Konishi
Digital Architecture Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo 135-0064, Japan
1 shared publication
Latest Publications
- Open Access
- 22 December 2024
- Published by MDPI AG in Electronics
- Vol. 13 (24) , 5043
Stability Analysis of ChatGPT-Based Sentiment Analysis in AI Quality Assurance
In the era of large AI models, the intricate architectures and vast parameter sets of models such as large language models (LLMs) present significant challenges for effective AI quality management (AIQM). This paper investigates the quality assurance of a specific LLM-based AI product: ChatGPT-based sentiment analysis. The study focuses on stability issues, examining both the operation and robustness of ChatGPT’s underlying large-scale AI model. Through experimental analysis on benchmark datasets for sentiment analysis, the findings highlight the ChatGPT-based sentiment analysis’s susceptibility to uncertainty, which relates to various operational factors. Furthermore, the study reveals that the ChatGPT-based model faces stability challenges, particularly when confronted with conventional small-text adversarial attacks targeting robustness.
- 22 December 2024
- Published by MDPI AG in Electronics
- Vol. 13 (24) , 5043
Open AccessStability Analysis of ChatGPT-Based Sentiment Analysis in AI Quality Assurance
In the era of large AI models, the intricate architectures and vast parameter sets of models such as large language models (LLMs) present significant challenges for effective AI quality management (AIQM). This paper investigates the quality assurance of a specific LLM-based AI product: ChatGPT-based sentiment analysis. The study focuses on stability issues, examining both the operation and robustness of ChatGPT’s underlying large-scale AI model. Through experimental analysis on benchmark datasets for sentiment analysis, the findings highlight the ChatGPT-based sentiment analysis’s susceptibility to uncertainty, which relates to various operational factors. Furthermore, the study reveals that the ChatGPT-based model faces stability challenges, particularly when confronted with conventional small-text adversarial attacks targeting robustness.
- Open Access
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 126415-126425
On the Security of Learnable Image Encryption for Privacy-Preserving Deep Learning
In this paper, we evaluate the security of learnable image encryption methods proposed for privacy-preserving deep learning. In addition, we also propose a new generative model-based attack based on latent diffusion models. Various learnable encryption methods have been studied to protect the sensitive visual information of plain images, and some of them have been investigated to be robust enough against all existing attacks. However, previous attacks on image encryption focus only on traditional cryptanalytic attacks or reverse translation models, so these attacks cannot recover any visual information if a block-scrambling encryption step, which effectively destroys global information, is applied. Instead of reconstructing identical images as plain ones from encrypted images, generative models such as StyleGAN were previously explored to recover styles that can reveal identifiable information from the encrypted images. However, large-scale off-the-shelf latent diffusion models are not yet considered in this regard. Therefore, in this paper, we utilize Stable Diffusion as a generative model-based attack and evaluate the security of learnable image encryption. Experiments were carried out on various datasets, showing that images reconstructed by Stable Diffusion-based attack have some visual cues similar to plain images.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 126415-126425
Open AccessOn the Security of Learnable Image Encryption for Privacy-Preserving Deep Learning
In this paper, we evaluate the security of learnable image encryption methods proposed for privacy-preserving deep learning. In addition, we also propose a new generative model-based attack based on latent diffusion models. Various learnable encryption methods have been studied to protect the sensitive visual information of plain images, and some of them have been investigated to be robust enough against all existing attacks. However, previous attacks on image encryption focus only on traditional cryptanalytic attacks or reverse translation models, so these attacks cannot recover any visual information if a block-scrambling encryption step, which effectively destroys global information, is applied. Instead of reconstructing identical images as plain ones from encrypted images, generative models such as StyleGAN were previously explored to recover styles that can reveal identifiable information from the encrypted images. However, large-scale off-the-shelf latent diffusion models are not yet considered in this regard. Therefore, in this paper, we utilize Stable Diffusion as a generative model-based attack and evaluate the security of learnable image encryption. Experiments were carried out on various datasets, showing that images reconstructed by Stable Diffusion-based attack have some visual cues similar to plain images.
- Open Access
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 5, 902-913
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-Trained Models
In this paper, we propose key-based defense model proliferation by leveraging pre-trained models and utilizing recent efficient fine-tuning techniques on ImageNet-1k classification. First, we stress that deploying key-based models on edge devices is feasible with the latest model deployment advancements, such as Apple CoreML, although the mainstream enterprise edge artificial intelligence (Edge AI) has been focused on the Cloud. Then, we point out that the previous key-based defense on on-device image classification is impractical for two reasons: (1) training many classifiers from scratch is not feasible, and (2) key-based defenses still need to be thoroughly tested on large datasets like ImageNet. To this end, we propose to leverage pre-trained models and utilize efficient fine-tuning techniques to proliferate key-based models even on limited compute resources. Experiments were carried out on the ImageNet-1k dataset using adaptive and non-adaptive attacks. The results show that our proposed fine-tuned key-based models achieve a superior classification accuracy (more than 10% increase) compared to the previous key-based models on classifying clean and adversarial examples.
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 5, 902-913
Open AccessEfficient Key-Based Adversarial Defense for ImageNet by Using Pre-Trained Models
In this paper, we propose key-based defense model proliferation by leveraging pre-trained models and utilizing recent efficient fine-tuning techniques on ImageNet-1k classification. First, we stress that deploying key-based models on edge devices is feasible with the latest model deployment advancements, such as Apple CoreML, although the mainstream enterprise edge artificial intelligence (Edge AI) has been focused on the Cloud. Then, we point out that the previous key-based defense on on-device image classification is impractical for two reasons: (1) training many classifiers from scratch is not feasible, and (2) key-based defenses still need to be thoroughly tested on large datasets like ImageNet. To this end, we propose to leverage pre-trained models and utilize efficient fine-tuning techniques to proliferate key-based models even on limited compute resources. Experiments were carried out on the ImageNet-1k dataset using adaptive and non-adaptive attacks. The results show that our proposed fine-tuned key-based models achieve a superior classification accuracy (more than 10% increase) compared to the previous key-based models on classifying clean and adversarial examples.
- 29 May 2022
- Published by Springer Nature
- p. 149-167
Adversarial Defense with Secret Key
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE MultiMedia
- Vol. 29 (2) , 23-33
Privacy-Preserving Image Classification Using an Isotropic Network
In this article, we propose a privacy-preserving image classification method that uses encrypted images and an isotropic network, such as the vision transformer. The proposed method allows us not only to apply images without visual information to deep neural networks for both training and testing, but also to maintain a high classification accuracy. In addition, compressible encrypted images, called encryption-then-compression (EtC) images, can be used for both training and testing without any adaptation network. Previously, to classify EtC images, an adaptation network was required before a classification network, so methods with an adaptation network have been only tested on small images. To the best of our knowledge, previous privacy-preserving image classification methods have never considered image compressibility and patch embedding-based isotropic networks. In an experiment, the proposed privacy-preserving image classification was demonstrated to outperform state-of-the-art methods even when EtC images were used in terms of classification accuracy and robustness against various attacks under the use of two isotropic networks: vision transformer and ConvMixer.
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE MultiMedia
- Vol. 29 (2) , 23-33
Privacy-Preserving Image Classification Using an Isotropic Network
In this article, we propose a privacy-preserving image classification method that uses encrypted images and an isotropic network, such as the vision transformer. The proposed method allows us not only to apply images without visual information to deep neural networks for both training and testing, but also to maintain a high classification accuracy. In addition, compressible encrypted images, called encryption-then-compression (EtC) images, can be used for both training and testing without any adaptation network. Previously, to classify EtC images, an adaptation network was required before a classification network, so methods with an adaptation network have been only tested on small images. To the best of our knowledge, previous privacy-preserving image classification methods have never considered image compressibility and patch embedding-based isotropic networks. In an experiment, the proposed privacy-preserving image classification was demonstrated to outperform state-of-the-art methods even when EtC images were used in terms of classification accuracy and robustness against various attacks under the use of two isotropic networks: vision transformer and ConvMixer.
- Open Access
Access Control of Object Detection Models Using Encrypted Feature Maps
In this paper, we propose an access control method for object detection models. The use of encrypted images or encrypted feature maps has been demonstrated to be effective in access control of models from unauthorized access. However, the effectiveness of the approach has been confirmed in only image classification models and semantic segmentation models, but not in object detection models. In this paper, the use of encrypted feature maps is shown to be effective in access control of object detection models for the first time.
Open AccessAccess Control of Object Detection Models Using Encrypted Feature Maps
In this paper, we propose an access control method for object detection models. The use of encrypted images or encrypted feature maps has been demonstrated to be effective in access control of models from unauthorized access. However, the effectiveness of the approach has been confirmed in only image classification models and semantic segmentation models, but not in object detection models. In this paper, the use of encrypted feature maps is shown to be effective in access control of object detection models for the first time.
- Open Access
- 9 July 2021
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 10 (1)
A protection method of trained CNN model with a secret key from unauthorized access
In this paper, we propose a novel method for protecting convolutional neural network models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enables us to protect not only from copyright infringement but also the functionality of a model from unauthorized access without any noticeable overhead. We introduce three block-wise transformations with a secret key set to generate learnable transformed images: pixel shuffling, negative/positive transformation, and format-preserving Feistel-based encryption. Protected models are trained by using transformed images. The results of experiments with the CIFAR and ImageNet datasets show that the performance of a protected model was close to that of non-protected models when the key set was correct, while the accuracy severely dropped when an incorrect key set was given. The protected model was also demonstrated to be robust against various attacks. Compared with the state-of-the-art model protection with passports, the proposed method does not have any additional layers in the network, and therefore, there is no overhead during training and inference processes.
- 9 July 2021
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 10 (1)
Open AccessA protection method of trained CNN model with a secret key from unauthorized access
In this paper, we propose a novel method for protecting convolutional neural network models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enables us to protect not only from copyright infringement but also the functionality of a model from unauthorized access without any noticeable overhead. We introduce three block-wise transformations with a secret key set to generate learnable transformed images: pixel shuffling, negative/positive transformation, and format-preserving Feistel-based encryption. Protected models are trained by using transformed images. The results of experiments with the CIFAR and ImageNet datasets show that the performance of a protected model was close to that of non-protected models when the key set was correct, while the accuracy severely dropped when an incorrect key set was given. The protected model was also demonstrated to be robust against various attacks. Compared with the state-of-the-art model protection with passports, the proposed method does not have any additional layers in the network, and therefore, there is no overhead during training and inference processes.
- Open Access
- 22 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 64629-64638
Image to Perturbation: An Image Transformation Network for Generating Visually Protected Images for Privacy-Preserving Deep Neural Networks
We propose a novel image transformation network for generating visually protected images for privacy-preserving deep neural networks (DNNs). The proposed transformation network is trained by using a plain image dataset so that plain images are converted into visually protected ones. Conventional perceptual encryption methods cause some accuracy degradation in image classification and are not robust enough against state-of-the-art attacks. In contrast, the proposed network not only enables us to maintain the image classification accuracy that using plain images achieves but is also strongly robust against attacks including DNN-based ones. Furthermore, there is no need to manage any security keys as the conventional methods require. In an image classification experiment, the proposed network is demonstrated to strongly protect the visual information of plain images while maintaining a high classification accuracy under the use of two typical classification networks: ResNet and VGG. In addition, it is shown that the visually protected images are robust enough against various attacks in an experiment in which we tried to restore the visual information of plain images.
- 22 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 64629-64638
Open AccessImage to Perturbation: An Image Transformation Network for Generating Visually Protected Images for Privacy-Preserving Deep Neural Networks
We propose a novel image transformation network for generating visually protected images for privacy-preserving deep neural networks (DNNs). The proposed transformation network is trained by using a plain image dataset so that plain images are converted into visually protected ones. Conventional perceptual encryption methods cause some accuracy degradation in image classification and are not robust enough against state-of-the-art attacks. In contrast, the proposed network not only enables us to maintain the image classification accuracy that using plain images achieves but is also strongly robust against attacks including DNN-based ones. Furthermore, there is no need to manage any security keys as the conventional methods require. In an image classification experiment, the proposed network is demonstrated to strongly protect the visual information of plain images while maintaining a high classification accuracy under the use of two typical classification networks: ResNet and VGG. In addition, it is shown that the visually protected images are robust enough against various attacks in an experiment in which we tried to restore the visual information of plain images.
- 1 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 2709-2723
Block-Wise Image Transformation With Secret Key for Adversarially Robust Defense
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 for adversarially robust defense. The proposed transformation is a block-wise preprocessing technique with a secret key to input images. The proposed defense obfuscates gradients in the absence of the secret key unlike previously defeated obfuscating defenses. We developed three algorithms to realize the proposed transformation: Pixel Shuffling, Bit Flipping, and FFX Encryption. Experiments were carried out on the CIFAR-10 and ImageNet datasets by using both black-box and white-box attacks with various metrics including adaptive ones. The results show that the proposed defense achieves high accuracy close to that of using clean images even under adaptive attacks for the first time. In the best-case scenario, a model trained by using images transformed by FFX Encryption (block size of 4) yielded an accuracy of 92.30% on clean images and 91.48% under PGD attack with a noise distance of 8/255, which is close to the non-robust accuracy (95.45%) for the CIFAR-10 dataset, and it yielded an accuracy of 72.18% on clean images and 71.43% under the same attack, which is also close to the standard accuracy (73.70%) for the ImageNet dataset. Overall, all three proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack.
- 1 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 2709-2723
Block-Wise Image Transformation With Secret Key for Adversarially Robust Defense
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 for adversarially robust defense. The proposed transformation is a block-wise preprocessing technique with a secret key to input images. The proposed defense obfuscates gradients in the absence of the secret key unlike previously defeated obfuscating defenses. We developed three algorithms to realize the proposed transformation: Pixel Shuffling, Bit Flipping, and FFX Encryption. Experiments were carried out on the CIFAR-10 and ImageNet datasets by using both black-box and white-box attacks with various metrics including adaptive ones. The results show that the proposed defense achieves high accuracy close to that of using clean images even under adaptive attacks for the first time. In the best-case scenario, a model trained by using images transformed by FFX Encryption (block size of 4) yielded an accuracy of 92.30% on clean images and 91.48% under PGD attack with a noise distance of 8/255, which is close to the non-robust accuracy (95.45%) for the CIFAR-10 dataset, and it yielded an accuracy of 72.18% on clean images and 71.43% under the same attack, which is also close to the standard accuracy (73.70%) for the ImageNet dataset. Overall, all three proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack.
- Open Access
- 9 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177932-177943
Adversarial Robustness by One Bit Double Quantization for Visual Classification
In this paper, we propose a novel robust visual classification framework that uses double quantization (dquant) to defend against adversarial examples in a specific attack scenario called “subsequent adversarial examples” where test images are injected with adversarial noise. The proposed system can remove the adversarial noise completely on this particular attack scenario. First, we analyze the potential sources of adversarial noise and classify adversarial examples into three classes. We then propose a novel effective solution, dquant, to target a specific class of adversarial examples. The first quantization is 1–bit dithering applied to both training and test images. The second one is linear quantization, which is applied to test images just before being inputted to a model to remove any adversarial noise. The linear quantizer guarantees that original 1–bit test images will be restored regardless of adversarial noise distance, and, therefore, dquant maintains identical accuracy whether or not the model is under attack. The results show that dquant achieves comparable accuracy, 85.28% on the CIFAR-10 and 94.99% on the Oxford-IIIT Pet datasets against three state-of-the-art adversaries with even a previously untested maximum adversarial distance of 64.
- 9 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177932-177943
Open AccessAdversarial Robustness by One Bit Double Quantization for Visual Classification
In this paper, we propose a novel robust visual classification framework that uses double quantization (dquant) to defend against adversarial examples in a specific attack scenario called “subsequent adversarial examples” where test images are injected with adversarial noise. The proposed system can remove the adversarial noise completely on this particular attack scenario. First, we analyze the potential sources of adversarial noise and classify adversarial examples into three classes. We then propose a novel effective solution, dquant, to target a specific class of adversarial examples. The first quantization is 1–bit dithering applied to both training and test images. The second one is linear quantization, which is applied to test images just before being inputted to a model to remove any adversarial noise. The linear quantizer guarantees that original 1–bit test images will be restored regardless of adversarial noise distance, and, therefore, dquant maintains identical accuracy whether or not the model is under attack. The results show that dquant achieves comparable accuracy, 85.28% on the CIFAR-10 and 94.99% on the Oxford-IIIT Pet datasets against three state-of-the-art adversaries with even a previously untested maximum adversarial distance of 64.