• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.3
• /
• pp.135-142
• /
• 2017

DDoS (Distributed Denial of Service) exhausts the target server's resources using the large number of zombie pc, As a result normal users don't access to server. DDoS Attacks steadly increase by many attacker, and almost target of the attack is critical system such as IT Service Provider, Government Agency, Financial Institution. In this paper, We will introduce the CNN (Convolutional Neural Network) of deep learning based real-time detection system for DNS amplification Attack (DNS DDoS Attack). We use the dataset which is mixed with collected data in the real environment in order to overcome existing research limits that use only the data collected in the experiment environment. Also, we build a deep learning model based on Convolutional Neural Network (CNN) that is used in pattern recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2512-2531
• /
• 2014

We propose a new Distributed Denial of Service (DDoS) defense mechanism that protects http web servers from application-level DDoS attacks based on the two methodologies: whitelist-based admission control and busy period-based attack flow detection. The attack flow detection mechanism detects attach flows based on the symptom or stress at the server, since it is getting more difficult to identify bad flows only based on the incoming traffic patterns. The stress is measured by the time interval during which a given client makes the server busy, referred to as a client-induced server busy period (CSBP). We also need to protect the servers from a sudden surge of attack flows even before the malicious flows are identified by the attack flow detection mechanism. Thus, we use whitelist-based admission control mechanism additionally to control the load on the servers. We evaluate the performance of the proposed scheme via simulation and experiment. The simulation results show that our defense system can mitigate DDoS attacks effectively even under a large number of attack flows, on the order of thousands, and the experiment results show that our defense system deployed on a linux machine is sufficiently lightweight to handle packets arriving at a rate close to the link rate.

• ETRI Journal
• /
• v.41 no.5
• /
• pp.560-573
• /
• 2019

Two supervised learning algorithms, a basic neural network and a long short-term memory recurrent neural network, are applied to traffic including DDoS attacks. The joint effects of preprocessing methods and hyperparameters for machine learning on performance are investigated. Values representing attack characteristics are extracted from datasets and preprocessed by two methods. Binary classification and two optimizers are used. Some hyperparameters are obtained exhaustively for fast and accurate detection, while others are fixed with constants to account for performance and data characteristics. An experiment is performed via TensorFlow on three traffic datasets. Three scenarios are considered to investigate the effects of learning former traffic on sequential traffic analysis and the effects of learning one dataset on application to another dataset, and determine whether the algorithms can be used for recent attack traffic. Experimental results show that the used preprocessing methods, neural network architectures and hyperparameters, and the optimizers are appropriate for DDoS attack detection. The obtained results provide a criterion for the detection accuracy of attacks.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.1-7
• /
• 2012

DDoS attack is a malicious attempt to exhaust resources of target system and network capacities using lots of distributed zombi systems. DDoS attack introduced in early 2000 has being evolved over time and presented in a various form of attacks. This paper proposes a scheme to detect DDoS attacks and to reduce possibility of such attacks that are especially based on vulnerabilities presented by using control packets of existing network protocols. To cope with DDoS attacks, the proposed scheme utilizes a buffer management techniques commonly used for congestion control in Internet. Our scheme is not intended to detect DDoS attacks perfectly but to minimize possibility of overloading of internal system and to mitigate possibility of attacks by discarding control packets at the time of detecting DDoS attacks. In addition, the detection module of our scheme can adapt dynamically to instantly increasing traffic unlike previously proposed schemes.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.4
• /
• pp.809-817
• /
• 2012

One of the OSI 7 Layer DDoS Attack, HTTP POST DDoS can deny legitimate service by web server resource depletion. This Attack can be executed with less network traffic and legitimate TCP connections. Therefore, It is difficult to distinguish DDoS traffic from legitimate users. In this paper, I propose an anomaly HTTP POST traffic detection algorithm and http each page Content-Length field size limit with defense method for HTTP POST DDoS attack. Proposed method showed the result of detection and countermeasure without false negative and positive to use the r-u-dead-yet of HTTP POST DDoS attack tool and the self-developed attack tool.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.596-605
• /
• 2016

Since the Denial of Service Attack against multiple targets in the Korean network in private and public sectors in 2009, Korea has spent a great amount of its budget to build strong Internet infrastructure against DDoS attacks. As a result of the investments, many major governments and corporations installed dedicated DDoS defense systems. However, even organizations equipped with the product based defense system often showed incompetency in dealing with DDoS attacks with little variations from known attack types. In contrast, by following a capacity centric DDoS detection method, defense personnel can identify various types of DDoS attacks and abnormality of the system through checking availability of service resources, regardless of the types of specific attack techniques. Thus, the defense personnel can easily derive proper response methods according to the attacks. Deviating from the existing DDoS defense framework, this research study introduces a capacity centric DDoS detection methodology and provides methods to mitigate DDoS attacks by applying the methodology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2555-2562
• /
• 2009

The algorithm that is proposed in this paper defined a probability function to count connection process and connection-end process to apply TRW algorithm to voice network. Set threshold to evaluate the algorithm that is proposed, Based on the type of connection attack traffic changing the probability to measure the effectiveness of the algorithm, and Attack packets based on the speed of attack detection time was measured. At the result of evaluation, proposed algorithm shows that DDoS attack starts at 10 packets per a second and it detects the attack after 1.2 seconds from the start. Moreover, it shows that the algorithm detects the attack in 0.5 second if the packets were 20 per a second.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2149-2170
• /
• 2017

Application-layer Distributed Denial-of-Service (DDoS) attack is one of the leading security problems in the Internet. In recent years, the attack strategies of application-layer DDoS have rapidly developed. This paper introduces a new attack strategy named Path Vulnerabilities-Based (PVB) attack. In this attack strategy, an attacker first analyzes the contents of web pages and subsequently measures the actual response time of each webpage to build a web-resource-weighted-directed graph. The attacker uses a Top M Longest Path algorithm to find M DDoS vulnerable paths that consume considerable resources when sequentially accessing the pages following any of those paths. A detection mechanism for such attack is also proposed and discussed. A finite-state machine is used to model the dynamical processes for the state of the user's session and monitor the PVB attacks. Numerical results based on real-traffic simulations reveal the efficiency of the attack strategy and the detection mechanism.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.189-194
• /
• 2005

Present hacking technology is undergone a change on the distributed DoS Attack which cause a lot of traffic to the network or single host. In this paper, with giving mobility to the mean deviation per protocol and it's field, and with adapting pattern matching approach to DDoS attack detection technique, we propose a method to detect the DDoS attack, to have less misdetection and to detect these attacks correctly.

• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.49-55
• /
• 2004

DDoS is an attack type that interfere with normal service by running out network bandwidth, process throughput, and system resource. It can be recognized intuitively by network slowdown and connection impossibility state, but it is necessary to detect DDoS attack by exact and quantitative analysis. In this paper, the exact and efficient DDoS attack detection system which is able to detect traffic flooding by MIB information, and attack traffic by packet analysis is proposed and realized.