• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.57-64
• /
• 2023

In this study, we analyzed how to steal the target model without training data. Input data is generated using the generative model, and a similar model is created by defining a loss function so that the predicted values of the target model and the similar model are close to each other. At this time, the target model has a process of learning so that the similar model is similar to it by gradient descent using the logit (logic) value of each class for the input data. The tensorflow machine learning library was used as an experimental environment, and CIFAR10 and SVHN were used as datasets. A similar model was created using the ResNet model as a target model. As a result of the experiment, it was found that the model stealing method generated a similar model with an accuracy of 86.18% for CIFAR10 and 96.02% for SVHN, producing similar predicted values to the target model. In addition, considerations on the model stealing method, military use, and limitations were also analyzed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4909-4926
• /
• 2020

Cyberattacks penetrate the server and perform various malicious acts such as stealing confidential information, destroying systems, and exposing personal information. To achieve this, attackers perform various malicious actions by infecting endpoints and accessing the internal network. However, the current countermeasures are only anti-viruses that operate in a signature or pattern manner, allowing initial unknown attacks. Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking. If you fail to respond to the initial attack, it is difficult to respond additionally because malicious behavior like Advanced Persistent Threat (APT) attack does not occur immediately, but occurs over a long period of time. In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus. The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning. The experiment trained a dataset collected over a month in a real-world commercial endpoint environment, and tested the data collected over the next month. As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through VirusTotal (VT). In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1031-1041
• /
• 2020

Cloud computing technology plays an important role in the deep learning industry as deep learning services are deployed frequently on top of cloud infrastructures. In such cloud environment, virtualization technology provides logically independent and isolated computing space for each tenant. However, recent studies demonstrate that by leveraging vulnerabilities of virtualization techniques and shared processor architectures in the cloud system, various side-channels can be established between cloud tenants. In this paper, we propose a novel attack scenario that can steal internal information of deep learning models by exploiting the Meltdown vulnerability in a multi-tenant system environment. On the basis of our experiment, the proposed attack method could extract internal information of a TensorFlow deep-learning service with 92.875% accuracy and 1.325kB/s extraction speed.