公开(公告)号：US20220343031A1

公开(公告)日：2022-10-27

申请号：US17333198

申请日：2021-05-28

Applicant: Korea University Research and Business Foundation

Inventor： Hodong KIM ,  Junbeom HUR

IPC: G06F21/75 ,  G06N20/00 ,  G06N5/04

Abstract: Disclosed are an apparatus for detecting a cache side-channel attack which is capable of quickly detecting the cache side-channel attack in real time with high accuracy and a method thereof. The apparatus for detecting the cache side-channel attack may include a data collection unit that collects data from at least one of a core, an L1 cache, an L2 cache, and an L3 cache, respectively, and a data collection unit that collects data from at least one of a core, an L1 cache, an L2 cache, and an L3 cache, respectively.

公开(公告)号：US20240220627A1

公开(公告)日：2024-07-04

申请号：US18028851

申请日：2021-09-28

Applicant: KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION

Inventor： Hoyong JEONG ,  Do-Hyun RYU ,  Junbeom HUR

IPC: G06F21/57

CPC classification number: G06F21/577 ,  G06F2221/033

Abstract: An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the steps of: acquiring a page table of a process to be attacked; acquiring, on the basis of the page table, heap area data of the process to be attacked; acquiring, on the basis of the heap area data, an artificial neural network instance of the process to be attacked; and extracting a structure of an artificial neural network model on the basis of the artificial neural network instance.

公开(公告)号：US20230196745A1

公开(公告)日：2023-06-22

申请号：US18077599

申请日：2022-12-08

Applicant: Korea University Research and Business Foundation

Inventor： Junbeom HUR ,  Minjae KIM ,  Gyeongsup LIM

IPC: G06V10/776 ,  G06V10/82 ,  G06T3/40

CPC classification number: G06V10/776 ,  G06V10/82 ,  G06T3/4046 ,  G06T3/4053

Abstract: Disclosed is a method for performing an adversarial attack by a computing device including one or more processors, which may include: generating a first conversion image by inputting an original image into a first neural network model; generating first object detection result data by inputting the first conversion image into a second neural network model; generating first noise based on a first loss value between the first object detection result data and a prestored ground-truth; generating a first adversarial image based on the first noise and the first conversion image; generating second noise based on a second loss value between the first adversarial image and the first conversion image; and generating a second adversarial image based on the second noise and the original image.