Application-layer Distributed Denial-of-Service (DDoS) attack takes advantage of the complexity and diversity of network protocols and services. This kind of attacks is more difficult to prevent than other kinds of DDoS attacks. This paper introduces a novel detection mechanism for application-layer DDoS attack based on a One-Class Support Vector Machine (OC-SVM). Support vector machine (SVM) is a relatively new machine learning technique based on statistics. OC-SVM is a special variant of the SVM and since only the normal data is required for training, it is effective for detection of application-layer DDoS attack. In this detection strategy, we first extract 7 features from normal users' sessions. Then, we build normal users' browsing models by using OC-SVM. Finally, we use these models to detect application-layer DDoS attacks. Numerical results based on simulation experiments demonstrate the efficacy of our detection method.
Abstract. Lots of methods have been proposed to detect Distributed Denial-of-Service (DDoS) attacks focus on the transport layer and the network layer. However, these methods may not work well when application-layer DDoS attack is launched. In this paper, we introduce a clustering method based on some features to detect application-layer DDoS attack. Firstly, we extract features from normal users' sessions. Then, we cluster users' sessions by K-means algorithm and build normal users' behavior model. Finally, we detect the application-layer DDoS attack based on the normal users' behavior model.
Background
The present study aimed to compare the effects of the combined administration of two adjuvants, dopamine and phenylephrine, on the cutaneous analgesic effect and duration of mexiletine in rats.
Methods
Nociceptive blockage was evaluated by the inhibition of response to skin pinpricks in rats via the cutaneous trunci muscle reflex (CTMR). After subcutaneous injection, the analgesic activities of mexiletine in the absence and presence of either dopamine or phenylephrine were assessed. Each injection was standardized into 0.6 ml with a mixture of drugs and saline.
Results
Subcutaneous injections of mexiletine successfully induced dose-dependent cutaneous analgesia in rats. The results revealed that rats injected with 1.8 μmol mexiletine exhibited 43.75% blockage (%MPE), while rats injected with 6.0 μmol mexiletine showed 100% blockage. Co-application of mexiletine (1.8 or 6.0 μmol) with dopamine (0.06, 0.60, or 6.00 μmol) elicited full sensory block (%MPE). Sensory blockage ranged from 81.25% to 95.83% in rats injected with mexiletine (1.8 μmol) and phenylephrine (0.0059 or 0.0295 μmol), and complete subcutaneous analgesia was observed in rats injected with mexiletine (1.8 μmol) and a higher concentration of phenylephrine (0.1473 μmol). Furthermore, mexiletine at 6.0 μmol completely blocked nociception when combined with any concentration of phenylephrine, while 0.1473 μmol phenylephrine alone exhibited 35.417% subcutaneous analgesia. The combined application of dopamine (0.06/0.6/6 μmol) and mexiletine (1.8/6 μmol) resulted in increased %MPE, complete block time, full recovery time, and AUCs compared to the combined application of phenylephrine (0.0059 and 0.1473 μmol) and mexiletine (1.8/6 μmol) (p < 0.001).
Conclusion
Dopamine is superior to phenylephrine in improving sensory blockage and enhancing the duration of nociceptive blockage by mexiletine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.