A Collaborative DDoS Mitigation Solution Based on Ethereum Smart Contract and RNN-LSTM
Title | A Collaborative DDoS Mitigation Solution Based on Ethereum Smart Contract and RNN-LSTM |
Publication Type | Conference Paper |
Year of Publication | 2019 |
Authors | Essaid, Meryam, Kim, DaeYong, Maeng, Soo Hoon, Park, Sejin, Ju, Hong Taek |
Conference Name | 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS) |
Keywords | attack traffic flow, autonomous systems, blockchain, blockchain technology, Collaboration, collaborative DDoS mitigation solution, collaborative protection mitigation, complex configuration, composability, Computer crime, computer network security, coordinated DDoS mitigation approaches, cryptocurrencies, DDoS attack mitigation, ddos mitigation, Deep Learning, Deep learning DDoS detection system, defence capabilities, defence mechanisms, defence systems, distributed denial-of-service, effective DDoS defence, ethereum, ethereum smart contract, hardware resources, Human Behavior, individual DDoS attack class, learning (artificial intelligence), Lightning, Metrics, mitigation technique, pubcrawl, recurrent neural nets, resilience, Resiliency, RNN-LSTM, signalling DDoS system, smart contracts, telecommunication signalling, telecommunication traffic |
Abstract | Recently Distributed Denial-of-Service (DDoS) are becoming more and more sophisticated, which makes the existing defence systems not capable of tolerating by themselves against wide-ranging attacks. Thus, collaborative protection mitigation has become a needed alternative to extend defence mechanisms. However, the existing coordinated DDoS mitigation approaches either they require a complex configuration or are highly-priced. Blockchain technology offers a solution that reduces the complexity of signalling DDoS system, as well as a platform where many autonomous systems (Ass) can share hardware resources and defence capabilities for an effective DDoS defence. In this work, we also used a Deep learning DDoS detection system; we identify individual DDoS attack class and also define whether the incoming traffic is legitimate or attack. By classifying the attack traffic flow separately, our proposed mitigation technique could deny only the specific traffic causing the attack, instead of blocking all the traffic coming towards the victim(s). |
DOI | 10.23919/APNOMS.2019.8892947 |
Citation Key | essaid_collaborative_2019 |
- mitigation technique
- effective DDoS defence
- ethereum
- ethereum smart contract
- hardware resources
- Human behavior
- individual DDoS attack class
- learning (artificial intelligence)
- Lightning
- Metrics
- distributed denial-of-service
- pubcrawl
- recurrent neural nets
- resilience
- Resiliency
- RNN-LSTM
- signalling DDoS system
- smart contracts
- telecommunication signalling
- telecommunication traffic
- computer network security
- autonomous systems
- blockchain
- blockchain technology
- collaboration
- collaborative DDoS mitigation solution
- collaborative protection mitigation
- complex configuration
- composability
- Computer crime
- attack traffic flow
- coordinated DDoS mitigation approaches
- cryptocurrencies
- DDoS attack mitigation
- ddos mitigation
- deep learning
- Deep learning DDoS detection system
- defence capabilities
- defence mechanisms
- defence systems