• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.621-623
• /
• 2023

본 논문에서는 기계 학습 모델의 취약점과 대응책에 초점을 맞추어 적대적인 기계 학습 공격 및 방어 분야를 탐구한다. 신중하게 만들어진 입력 데이터를 도입하여 기계 학습 모델을 속이거나 조작하는 것을 목표로 하는 적대적 공격에 대한 심층 분석을 제공한다. 이 논문은 회피 및 독성 공격을 포함한 다양한 유형의 적대적 공격을 조사하고 기계 학습 시스템의 안정성과 보안에 대한 잠재적 영향을 조사한다. 또한 적대적 공격에 대한 기계 학습 모델의 견고성을 향상시키기 위해 다양한 방어 메커니즘과 전략을 제안하고 평가한다. 본 논문은 광범위한 실험과 분석을 통해 적대적 기계 학습에 대한 이해에 기여하고 효과적인 방어 기술에 대한 통찰력을 제공하는 것을 목표로 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.231-241
• /
• 2006

When current cyber attacks to information and communication facilities are examined, technologies such as chase evasion technology and defense deviation technology have been rapidly advanced and many weak systems worldwide are often used as passages. And when newly-developed cyber attack instruments are examined, technologies for prefect crimes such as weakness attack, chase evasion and evidence destruction have been developed and distributed in packages. Therefore, there is a limit to simple prevention technology and according to cases, special procedures such as real-time chase are required to overcome cyber crimes. Further, cyber crimes beyond national boundaries require to be treated in international cooperation and relevant procedural arrangements through which the world can fight against them together. However, in current laws, there are only regulations such as substantial laws including simple regulations on Punishment against violation. In procedure, they are treated based on the same procedure as that of general criminal cases which are offline crimes. In respect to international cooperation system, international criminal private law cooperation is applied based on general criminals, which brings many problems. Therefore, this study speculates the procedural law on cyber crimes and presents actual problems of our country and its countermeasures.

• The KIPS Transactions:PartC
• /
• v.12C no.1 s.97
• /
• pp.45-52
• /
• 2005

A damage scale of information property has been increasing rapidly by various illegal actions of information systems, which result from dysfunction of a knowledge society. Reinforcement in criminal investigation requests of network security has accelerated research and development of Intrusion Detection Systems(IDSs), which report intrusion-detection about these illegal actions. Due to limited designs of early IDSs, it is hard for the IDSs to cope with tricks to go around IDS as well as false-positive and false-negative trials in various network environments. In this paper, we showed that this kind of problems can be solved by using a Virtual Protocol Stack(VPS) that possesses automatic learning ability through an optimum-adaptive mobile code. Therefore, the enhanced IDS adapts dynamically to various network environments in consideration of monitored and self-learned network status. Moreover, it is shown that Insertion/Evasion attacks can be actively detected. Finally, we discussed that this method can be expanded to an intrusion detection technique that possesses adaptability in the various mixed network environments.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.193-203
• /
• 2022

After the everyday use of systems and applications of artificial intelligence in our world. Consequently, machine learning technologies have become characterized by exceptional capabilities and unique and distinguished performance in many areas. However, these applications and systems are vulnerable to adversaries who can be a reason to confer the wrong classification by introducing distorted samples. Precisely, it has been perceived that adversarial examples designed throughout the training and test phases can include industrious Ruin the performance of the machine learning. This paper provides a comprehensive review of the recent research on adversarial machine learning. It's also worth noting that the paper only examines recent techniques that were released between 2018 and 2021. The diverse systems models have been investigated and discussed regarding the type of attacks, and some possible security suggestions for these attacks to highlight the risks of adversarial machine learning.

• Convergence Security Journal
• /
• v.20 no.2
• /
• pp.111-121
• /
• 2020

Deep neural networks (DNNs) provide good performance for machine learning tasks such as image recognition and object recognition. However, DNNs are vulnerable to an adversarial example. An adversarial example is an attack sample that causes the neural network to recognize it incorrectly by adding minimal noise to the original sample. However, the disadvantage is that it takes a long time to generate such an adversarial example. Therefore, in some cases, an attack may be necessary that quickly causes the neural network to recognize it incorrectly. In this paper, we propose a fast misclassification sample that can rapidly attack neural networks. The proposed method does not consider the distortion of the original sample when adding noise. We used MNIST and CIFAR10 as experimental data and Tensorflow as a machine learning library. Experimental results show that the fast misclassification sample generated by the proposed method can be generated with 50% and 80% reduced number of iterations for MNIST and CIFAR10, respectively, compared to the conventional Carlini method, and has 100% attack rate.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.4
• /
• pp.437-445
• /
• 2023

A space system refers to a network of sensors, ground systems, and space-craft operating in space. The security of space systems relies on information systems and networks that support the design, launch, and operation of space missions. Characteristics of space operations, including command and control (C2) between space-craft (including satellites) and ground communication, also depend on wireless frequency and communication channels. Attackers can potentially engage in malicious activities such as destruction, disruption, and degradation of systems, networks, communication channels, and space operations. These malicious cyber activities include sensor spoofing, system damage, denial of service attacks, jamming of unauthorized commands, and injection of malicious code. Such activities ultimately lead to a decrease in the lifespan and functionality of space systems, and may result in damage to space-craft and, lead to loss of control. The Cybersecurity Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) matrix, proposed by Massachusetts Institute of Technology Research and Engineering (MITRE), consists of the following stages: Reconnaissance, Resource Development, Initial Access, Execution, Persistence, Privilege Escalation, Defense Evasion, Credential Access, Discovery, Lateral Movement, Collection, Command & Control, Exfiltration, and Impact. This paper identifies cybersecurity activities in space systems and satellite navigation systems through the National Institute of Standards and Technology (NIST)'s standard documents, former U.S. President Trump's executive orders, and presents risk management activities. This paper also explores cybersecurity's tactics attack techniques within the context of space systems (space-craft) by referencing the Sparta ATT&CK Matrix. In this paper, security threats in space systems analyzed, focusing on the cybersecurity attack tactics, techniques, and countermeasures of space-craft presented by Space Attack Research and Tactic Analysis (SPARTA). Through this study, cybersecurity attack tactics, techniques, and countermeasures existing in space-craft are identified, and an understanding of the direction of application in the design and implementation of safe small satellites is provided.

• IMMUNE NETWORK
• /
• v.4 no.2
• /
• pp.73-80
• /
• 2004

Viruses are obligate intracellular parasites which cause infection by invading and replicating within cells. The immune system has mechanisms which can attack the virus in extracellular and intracellular phase of life cycle, and which involve both non-specific and specific effectors. The survival of viruses depends on the survival of their hosts, and therefore the immune system and viruses have evolved together. Immune responses to viral infection may be variable depending on the site of infection, the mechanism of cell-to-cell spread of virus, physiology of the host, host genetic variation, and environmental condition. Viral infection of cells directly stimulates the production of interferons and they induce antiviral state in the surrounding cells. Complement system is also involved in the elimination of viruses and establishes the first line of defence with other non-specific immunity. During the course of viral infection, antibody is most effective at an early stage, especially before the virus enters its target cells. The virus- specific cytotoxic T lymphocytes are the principal effector cells in clearing established viral infections. But many viruses have resistant mechanism to host immune responses in every step of viral infection to cells. Some viruses have immune evasion mechanism and establish latency or persistency indefinitely. Furthermore antibodies to some viruses can enhance the disease by the second infection. Immune responses to viral infection are very different from those to bacterial infection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1419-1429
• /
• 2017

Recently, environment based authentication technique had proposed reinforced authentication, which generating statistical model per user after user login history classifies into account takeover or legitimate login. But reinforced authentication is likely to be attacked if user was not attacked in past. To improve this problem in this paper, we propose unconsciousness authentication technique that generates 2-Class user model, which trains user's environmental information and others' one using machine learning algorithms. To evaluate performance of proposed technique, we performed evasion attacks: non-knowledge attacker that does not know any information about user, and sophisticated attacker that only knows one information about user. Experimental results against non-knowledge attacker show that precision and recall of Class 0 were measured as 1.0 and 0.998 respectively, and experimental results against sophisticated attacker show that precision and recall of Class 0 were measured as 0.948 and 0.998 respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2805-2826
• /
• 2021

In most cases, the routing policy of networks shows a preference for a static one-to-one mapping of communication pairs to routing paths, which offers adversaries a great advantage to conduct thorough reconnaissance and organize an effective attack in a stress-free manner. With the evolution of network intelligence, some flexible and adaptive routing policies have already proposed to intensify the network defender to turn the situation. Routing mutation is an effective strategy that can invalidate the unvarying nature of routing information that attackers have collected from exploiting the static configuration of the network. However, three constraints execute press on routing mutation deployment in practical: insufficient route mutation space, expensive control costs, and incompatibility. To enhance the availability of route mutation, we propose an OpenFlow-based route mutation technique called Polymorphic Path Transferring (PPT), which adopts a physical and virtual path segment mixed construction technique to enlarge the routing path space for elevating the security of communication. Based on the Markov Decision Process, with considering flows distribution in the network, the PPT adopts an evolution routing path scheduling algorithm with a segment path update strategy, which relieves the press on the overhead of control and incompatibility. Our analysis demonstrates that PPT can secure data delivery in the worst network environment while countering sophisticated attacks in an evasion-free manner (e.g., advanced persistent threat). Case study and experiment results show its effectiveness in proactively defending against targeted attacks and its advantage compared with previous route mutation methods.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.288-294
• /
• 2021

There are various ways to be infected with malicious code due to the increase in Internet use, such as the web, affiliate programs, P2P, illegal software, DNS alteration of routers, word processor vulnerabilities, spam mail, and storage media. In addition, malicious codes are produced more easily than before through automatic generation programs due to evasion technology according to the advancement of production technology. In the past, the propagation speed of malicious code was slow, the infection route was limited, and the propagation technology had a simple structure, so there was enough time to study countermeasures. However, current malicious codes have become very intelligent by absorbing technologies such as concealment technology and self-transformation, causing problems such as distributed denial of service attacks (DDoS), spam sending and personal information theft. The existing malware detection technique, which is a signature detection technique, cannot respond when it encounters a malicious code whose attack pattern has been changed or a new type of malicious code. In addition, it is difficult to perform static analysis on malicious code to which code obfuscation, encryption, and packing techniques are applied to make malicious code analysis difficult. Therefore, in this paper, a method to detect malicious code through dynamic analysis and static analysis using Trojan-type Downloader/Dropper malicious code was showed, and suggested to malicious code detection and countermeasures.