• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.163-171
• /
• 2021

Recently, Machine Learning-based visualization approaches have been proposed to combat the problem of malware detection. Unfortunately, these techniques are exposed to Adversarial examples. Adversarial examples are noises which can deceive the deep learning based malware detection network such that the malware becomes unrecognizable. To address the shortcomings of these approaches, we present Block-matching and 3D filtering (BM3D) algorithm and deep image prior based denoising technique to defend against adversarial examples on visualization-based malware detection systems. The BM3D based denoising method eliminates most of the adversarial noise. After that the deep image prior based denoising removes the remaining subtle noise. Experimental results on the MS BIG malware dataset and benign samples show that the proposed denoising based defense recovers the performance of the adversarial attacked CNN model for malware detection to some extent.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.1-9
• /
• 2024

Although federated learning is designed to be safer than centralized methods in terms of security and privacy, it still has many vulnerabilities. An attacker performing an adversarial attack intentionally manipulates the deep learning model by injecting carefully crafted input data, that is, adversarial examples, into the client's training data to induce misclassification. A common defense strategy against this is so-called adversarial training, which involves preemptively learning the characteristics of adversarial examples into the model. Existing research assumes a scenario where all clients are under adversarial attack, but considering the number of clients in federated learning is very large, this is far from reality. In this paper, we experimentally examine aspects of adversarial training in a scenario where some of the clients are under attack. Through experiments, we found that there is a trade-off relationship in which the classification accuracy for normal samples decreases as the classification accuracy for adversarial examples increases. In order to effectively utilize this trade-off relationship, we present a method to perform adversarial training by adaptively selecting a loss function depending on whether the client is attacked.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.148-152
• /
• 2018

Adversarial attacks on artificial intelligence (AI) systems use adversarial examples to achieve the attack objective. Adversarial examples consist of slightly changed test data, causing AI systems to make false decisions on these examples. When used as a tool for attacking AI systems, this can lead to disastrous results. In this paper, we propose an ensemble of degraded convolutional neural network (CNN) modules, which is more robust to adversarial attacks than conventional CNNs. Each module is trained on degraded images. During testing, images are degraded using various degradation methods, and a final decision is made utilizing a one-hot encoding vector that is obtained by summing up all the output vectors of the modules. Experimental results show that the proposed ensemble network is more resilient to adversarial attacks than conventional networks, while the accuracies for normal images are similar.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1538-1552
• /
• 2021

Machine learning models are vulnerable to adversarial examples generated by adding a deliberately designed perturbation to a benign sample. Particularly, for automatic speech recognition (ASR) system, a benign audio which sounds normal could be decoded as a harmful command due to potential adversarial attacks. In this paper, we focus on the countermeasures against audio adversarial examples. By analyzing the characteristics of ASR systems, we find that frame offsets with silence clip appended at the beginning of an audio can degenerate adversarial perturbations to normal noise. For various scenarios, we exploit frame offsets by different strategies such as defending, detecting and hybrid strategy. Compared with the previous methods, our proposed method can defense audio adversarial example in a simpler, more generic and efficient way. Evaluated on three state-of-the-arts adversarial attacks against different ASR systems respectively, the experimental results demonstrate that the proposed method can effectively improve the robustness of ASR systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.449-458
• /
• 2023

Artificial Intelligence is providing convenience in various fields using big data and deep learning technologies. However, deep learning technology is highly vulnerable to adversarial examples, which can cause misclassification of classification models. This study proposes a method to detect and purification various adversarial attacks using StarGAN. The proposed method trains a StarGAN model with added Categorical Entropy loss using adversarial examples generated by various attack methods to enable the Discriminator to detect adversarial examples and the Generator to purification them. Experimental results using the CIFAR-10 dataset showed an average detection performance of approximately 68.77%, an average purification performance of approximately 72.20%, and an average defense performance of approximately 93.11% derived from restoration and detection performance.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.975-986
• /
• 2022

Deep learning is attracting great attention, showing excellent performance in image processing, but is vulnerable to adversarial attacks that cause the model to misclassify through perturbation on input data. Adversarial examples generated by adversarial attacks are minimally perturbated where it is difficult to identify, so visual features of the images are not generally changed. Unlikely deep learning models, people are not fooled by adversarial examples, because they classify the images based on such visual features of images. This paper proposes adversarial attack detection method using Symbolic Representation, which is a visual and symbolic features such as color, shape of the image. We detect a adversarial examples by comparing the converted Symbolic Representation from the classification results for the input image and Symbolic Representation extracted from the input images. As a result of measuring performance on adversarial examples by various attack method, detection rates differed depending on attack targets and methods, but was up to 99.02% for specific target attack.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.621-631
• /
• 2023

Adversarial training improves the robustness of deep neural networks for adversarial examples. However, the previous adversarial training method focuses only on the adversarial loss function, ignoring that even a small perturbation of the input layer causes a significant change in the hidden layer features. Consequently, the accuracy of a defended model is reduced for various untrained situations such as clean samples or other attack techniques. Therefore, an architectural perspective is necessary to improve feature representation power to solve this problem. In this paper, we apply an attention module that generates an attention map of an input image to a general model and performs PGD adversarial training upon the augmented model. In our experiments on the CIFAR-10 dataset, the attention augmented model showed higher accuracy than the general model regardless of the network structure. In particular, the robust accuracy of our approach was consistently higher for various attacks such as PGD, FGSM, and BIM and more powerful adversaries. By visualizing the attention map, we further confirmed that the attention module extracts features of the correct class even for adversarial examples.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1215-1225
• /
• 2021

Although Artificial Intelligence (AI) techniques have shown impressive performance in various fields, they are vulnerable to adversarial examples which induce misclassification by adding human-imperceptible perturbations to the input. Previous studies to defend the adversarial examples can be classified into three categories: (1) model retraining methods; (2) input transformation methods; and (3) adversarial examples detection methods. However, even though the defense methods against adversarial examples have constantly been proposed, there is no research to classify the type of adversarial attack. In this paper, we proposed an adversarial attack family classification method based on dimensionality reduction and clustering. Specifically, after extracting adversarial perturbation from adversarial example, we performed Linear Discriminant Analysis (LDA) to reduce the dimensionality of adversarial perturbation and performed K-means algorithm to classify the type of adversarial attack family. From the experimental results using MNIST dataset and CIFAR-10 dataset, we show that the proposed method can efficiently classify five tyeps of adversarial attack(FGSM, BIM, PGD, DeepFool, C&W). We also show that the proposed method provides good classification performance even in a situation where the legitimate input to the adversarial example is unknown.