Spam Detection Approach for Cloud Service Reviews Based on Probabilistic Ontology

Cloud computing is one of the high-demand services and prone to numerous types of attacks due to its Internet based backbone. Flooding based attack is one such type of attack over the cloud that exhausts the numerous resources and services of an individual or an enterprise by way of sending useless huge traffic. The nature of this traffic may be of slow or fast type. Flooding attacks are caused by way of sending massive volume of packets of TCP, UDP, ICMP traffic and HTTP Posts. The legitimate volume of traffic is suppressed and lost in traffic flooding traffics. Early detection of such attacks helps in minimization of the unauthorized utilization of resources on the target machine. Various inbuilt load balancing and scalability options to absorb flooding attacks are in use by cloud service providers up to ample extent still to maintain QoS at the same time by cloud service providers is a challenge. In this proposed technique. Change Point detection approach is proposed here to detect flooding DDOS attacks in cloud which are based on the continuous variant pattern of voluminous (flooding) traffic and is calculated by using various traffic data based metrics that are primary and computed in nature. Golden ration is used to compute the threshold and this threshold is further used along with the computed metric values of normal and malicious traffic for flooding attack detection. Traffic of websites is observed by using remote java script.

Download Full-text

Spam Detection Approaches with Case Study Implementation on Spam Corpora

Cases on ICT Utilization, Practice and Solutions ◽

10.4018/978-1-60960-015-0.ch012 ◽

2011 ◽

pp. 194-212

Author(s):

Biju Issac

Keyword(s):

Performance Test ◽

Detection Efficiency ◽

Detection Algorithm ◽

Spam Detection ◽

Network Bandwidth ◽

Detection Approach ◽

Study Implementation ◽

Keyword Searches ◽

E Mail

Email has been considered as one of the most efficient and convenient ways of communication since the users of the Internet has increased rapidly. E-mail spam, known as junk e-mail, UBE (unsolicited bulk e-mail) or UCE (unsolicited commercial e-mail), is the act of sending unwanted e-mail messages to e-mail users. Spam is becoming a huge problem to most users since it clutter their mailboxes and waste their time to delete all the spam before reading the legitimate ones. They also cost the user money with dial up connections, waste network bandwidth and disk space and make available harmful and offensive materials. In this chapter, initially we would like to discuss on existing spam technologies and later focus on a case study. Though many anti-spam solutions have been implemented, the Bayesian spam detection approach looks quite promising. A case study for spam detection algorithm is presented and its implementation using Java is discussed, along with its performance test results on two independent spam corpuses – Ling-spam and Enron-spam. We use the Bayesian calculation for single keyword sets and multiple keywords sets, along with its keyword contexts to improve the spam detection and thus to get good accuracy. The use of porter stemmer algorithm is also discussed to stem keywords which can improve spam detection efficiency by reducing keyword searches.

Download Full-text

Unsupervised Spammer Detection in Social Networks based on User Information Interests

10.21203/rs.3.rs-798887/v1 ◽

2021 ◽

Author(s):

Darshika Koggalahewa ◽

Yue Xu ◽

Ernest Foo

Keyword(s):

Social Networks ◽

Social Network ◽

Online Social Networks ◽

Supervised Classification ◽

Peer Acceptance ◽

Spam Detection ◽

Highly Active ◽

Detection Approach ◽

Data Fabrication ◽

Unsupervised Approach

Abstract Online Social Networks (OSNs) are a popular platform for communication and collaboration. Spammers are highly active in OSNs. Uncovering spammers has become one of the most challenging problems in OSNs. Classification-based supervised approaches are the most commonly used method for detecting spammers. The classification-based systems suffer from limitations of “data labelling”, “spam drift”, “imbalanced datasets” and “data fabrication”. These limitations effect the accuracy of a classifier’s detection. We present a pure unsupervised approach for spammer detection based on peer acceptance of a user in a social network to distinguish spammers from genuine users. The peer acceptance of a user to another user is calculated based on common shared interests over multiple shared topics between the two users. The main contribution of this paper is the introduction of a pure unsupervised spammer detection approach based on users’ peer acceptance. Our approach does not require labelled training datasets. While it does not better the accuracy of supervised classification-based approaches, our approach has become a successful alternative for traditional classifiers for spam detection by achieving an accuracy of 96.9%.

Download Full-text

An unsupervised method for social network spammer detection based on user information interests

Journal Of Big Data ◽

10.1186/s40537-021-00552-5 ◽

2022 ◽

Vol 9 (1) ◽

Author(s):

Darshika Koggalahewa ◽

Yue Xu ◽

Ernest Foo

Keyword(s):

Social Networks ◽

Social Network ◽

Online Social Networks ◽

Supervised Classification ◽

Peer Acceptance ◽

Spam Detection ◽

Highly Active ◽

Detection Approach ◽

Data Fabrication ◽

Unsupervised Approach

AbstractOnline Social Networks (OSNs) are a popular platform for communication and collaboration. Spammers are highly active in OSNs. Uncovering spammers has become one of the most challenging problems in OSNs. Classification-based supervised approaches are the most commonly used method for detecting spammers. Classification-based systems suffer from limitations of “data labelling”, “spam drift”, “imbalanced datasets” and “data fabrication”. These limitations effect the accuracy of a classifier’s detection. An unsupervised approach does not require labelled datasets. We aim to address the limitation of data labelling and spam drifting through an unsupervised approach.We present a pure unsupervised approach for spammer detection based on the peer acceptance of a user in a social network to distinguish spammers from genuine users. The peer acceptance of a user to another user is calculated based on common shared interests over multiple shared topics between the two users. The main contribution of this paper is the introduction of a pure unsupervised spammer detection approach based on users’ peer acceptance. Our approach does not require labelled training datasets. While it does not better the accuracy of supervised classification-based approaches, our approach has become a successful alternative for traditional classifiers for spam detection by achieving an accuracy of 96.9%.

Download Full-text