Computer Science And Technology - Research Publications
Permanent URI for this collectionhttps://kr.cup.edu.in/handle/32116/82
Browse
4 results
Search Results
Item DL-2P-DDoSADF: Deep learning-based two-phase DDoS attack detection framework(Elsevier Ltd, 2023-09-26T00:00:00) Mittal, Meenakshi; Kumar, Krishan; Behal, SunnyIn today's tech-driven world, while Internet-based applications drive social progress, their architectural weaknesses, inadequate security measures, lack of network segmentation, unsecured IoT devices etc., offer ample opportunities for attackers to launch a multitude of attacks on their services. Despite numerous security solutions, the frequent changes in the methods employed by attackers present a challenge for security systems to stay up to date. Moreover, the existing machine learning approaches are confined to known attack patterns and necessitate annotated data. This paper proposes a deep learning-based two-phase DDoS attack detection framework named DL-2P-DDoSADF. The proposed framework has been validated using the CICDDoS2019 and DDoS-AT-2022 datasets. In the first phase, Autoencoder (AE) has been trained using the legitimate traffic and threshold value has been set using Reconstruction Error (RE). The test data comprising legitimate and attack traffic has been used to validate the proposed approach efficacy. The initial phase entails utilizing a trained AE model to enable the passage of predicted legitimate traffic through the network. In contrast, the predicted attack traffic proceeds to the second phase to classify the type of attack it represents. The performance and efficacy of various deep learning approaches: Deep Neural Network (DNN), Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) are compared as part of the second phase. The autoencoder displayed an accuracy level of 99% in detecting both datasets in the initial phase. It has been observed that the DNN produced an overall accuracy of 97% and 96% for the CICDDoS2019 and DDoS-AT-2022 datasets, respectively, for multiclass classification. The DNN model performed better than LSTM and GRU models in the second phase. � 2023 Elsevier LtdItem Prevention of black hole attack over AODV and DSR MANET routing protocol(WARSE, 2015) Sharma, Shabnam; Mittal, MeenakshiWireless technology is one of the biggest contributions to mankind. In wireless system, transmission of information can be done without the need of wires and cables. Mobile Adhoc Networks (MANETs) do not have any centralized administration. They are infrastructure-less networks. They do not contain any networking device like routers or access points. MANETs are self-starting and dynamicnetwork comprising of mobile nodes. Mobile Ad-hoc networks require routing protocols for communication among nodes. Due to the lack of centralized management, various attacks are possible in MANETs such as passive or active attacks. Blackhole attack is an active kind of attack in which a malicious node pretendsto have a shortest and fresh path to the destination. Blackhole attack affects the performance by disrupting the normal communication in the network. Therefore, there is need to prevent the network from attack. In this paper, prevention of blackhole attack is done over AODV and DSR routing protocol with Random Waypoint Model. Malicious nodes in the network are known and if malicious nodes encounter in between the route from source to destination, then intermediate node have to simply discard that path and have to find an alternate path.The simulation results show that AODV routing protocol performs best and is suitable for highly dynamic networks.Item Prevention of Denial of Service Attack on Dynamic Source Routing VANET Protocol.(IJRET, 2015) Rani, Komal; Mittal, MeenakshiVehicular Ad Hoc Network (VANET) is a kind of Wireless Ad hoc Network in which node has high mobility, and thus the topology of the network is highly dynamic. VANET has thepotential to increase road safety, improve traffic efficiency as well as comfort to both drivers and passengers. There are different types of attacks possible on VANET. In this paper, implementation and prevention of DOS attack is done on topology based protocol- Dynamic Source Routing (DSR). The performance of DSR protocol is evaluated under different scenarios using Network Simulator (NS2), Simulation of Urban Mobility (SUMO) simulator and Mobility model generator for Vehicular networks(MOVE). The prevention scheme Queue Limiting Algorithm (QLA) proposed by Sinha & Mishra is implemented to prevent Denial of Service attack. The results show that DSR has high throughput and packet delivery ratio at low density of nodes and the value of these parameters become low at high density of nodes. The prevention scheme is capable to prevent DOS attack.Item Defence Mechanism of Distributed Reflective Denial of Service (DRDOS) Attack by using Hybrid (CPU-GPU) Computing System(IJCTT, 2015) Gagandeep; Mittal, MeenakshiDistributed Reflection Denial of Service (DRDOS) attack has become the daunting problem for businesses, system administrators, and computer system users. Distributed Reflective Denial of Service (DRDOS) attack typically exhausts bandwidth, processing capacity, or memory of a targeted machine, service or network. DRDOS attack reflects the traffic through reflector that becomes difficult to trace back the real attacker. Prevention and detection of a DRDOS attack is an important research topic for researchers throughout the world. Despite enormous efforts in combating DRDOS attacks in the past decade, DRDOS attacks are still a serious threat to the security of cyberspace. So a defence mechanism is used to combat the Distributed Reflected Denial of Service Attack by using additional hardware called Graphical Processing Unit (GPU) with victim�s machine called hybrid computing system. The results show that the hybrid (CPU-GPU) computing machine can handle the amplified response (i.e. 33 times more than the request packet) more efficiently than the normalmachine (with only CPU).