Longe Olumide

We present a novel client-side In-browser phishing detection plugin that can automatically detect and warn users about phishing websites in real-time, using pattern matching based on the random forest classifier. Random Forest classifier is established in literature to perform considerably well in detecting phishing websites. The advantages of the proposed method include improved privacy of users' browsing data and performance in spite of low network latency. The system was implemented mainly, using JavaScript, while the Random Forest classifier was trained on the phishing websites dataset using python scikit-learn. The learned model parameters were exported in a portable format for the plug-in to be lightweight; this was in consideration of the expected low-latent processing power of the client machines. To the best of our knowledge, this is the first implementation of phishing website detection In-browser plugin without the use of external web services; the plugin with a one-t...

With the current advancements of automation and robotics, it is expected that AI is going to transform the global economy in an exponential manner. To leverage the new opportunities, there is a need for preparation as well as learning and developing new skills for those new jobs. It is in this regard that Academic City is taking the AI agenda into the forefront, nurturing and empowering the African student to lead the continent into the new AI era. Academic City University College (ACity) is set to lead the sub-region in technology and innovation education with the introduction of an undergraduate degree in Artificial Intelligence (AI). The university becomes the first in Africa to offer a degree in AI. The program, which has commenced already forms part of the university’s short-term effort to develop a cadence of new programs that will invariably push the boundaries of knowledge while establishing a foothold for successful graduates in the jobs of the future. This paper projects t...

Recent growths in the use of email for communication and the corresponding growths in the volume of email received have made automatic processing of emails desirable. In tandem is the prevailing problem of Advance Fee fraud E-mails that pervades inboxes globally. These genres of e-mails solicit for financial transactions and funds transfers from unsuspecting users. Most modern mail-reading software packages provide some forms of programmable automatic filtering, typically in the form of sets of rules that file or otherwise dispose mails based on keywords detected in the headers or message body. Unfortunately programming these filters is an arcane and sometimes inefficient process. An adaptive mail system which can learn its users’ mail sorting preferences would therefore be more desirable. Premised on the work of Blanzieri & Bryl (2007), we proposes a framework dedicated to the phenomenon of locality in email data analysis of advance fee fraud e-mails which engages Support Vector Ma...

The internet has suffered from large forms of insecurity ranging from scamming, hacking and theft of information. Lately the use of CAPTCHAs has become a common security tool for authentication and authorization. However CAPTCHAS has suffered from certain vulnerabilities in the context of the simplicity offered by the challenge-response scenario and its timing which leaves room for improvement. This paper proposes a Time-Out Multiple Challenge-Response (C-R) CAPTCHA Framework that Utilizes Mathematical Modelling as a basis for overcoming some of the challenges faced by current CAPTCHA Systems. Our approach ensures security during the authorization and authentication process.

The inefficiencies of current spam filters against fraudulent (419) mails is not unrelated to the use by spammers of good-word attacks, topic drifts, parasitic spamming, wrong categorization and recategorization of electronic mails by e-mail clients and of course the fuzzy factors of greed and gullibility on the part of the recipients who responds to fraudulent spam mail offers. In this paper, we establish that mail token manipulations remain, above any other tactics, the most potent tool used by Nigerian scammers to fool statistical spam filters. While hoping that the uncovering of these manipulative evidences will prove useful in future antispam research, our findings also sensitize spam filter developers on the need to inculcate within their antispam architecture robust modules that can deal with the identified camouflages.

ABSTRACT The inefficiencies of current intrusion detection system against fraudulent cyber activities attracts the attention of computer gurus, also known as “hackers” to exploit known weakness on a particular host or network. These hackers are expert programmers who mainly focus on how the Internet works, and they interact with each other to know its strengths and weaknesses. Then they develop advanced tools which an average attacker with little background can use to know the liveness, reachability and running service on the network. Once an attacker identifies these details, he can accurately launch an effective attack and get maximum benefit out of it with less probability of attack detection. In this paper, a system that opens ports on a firewall by generating a connection attempt on a set of pre-specified closed ports is established. Once a correct sequence of connection attempts is received, the firewall rules are dynamically modified to allow the host that sent the connection attempts to connect over specific port(s). This conceals and protects network services which are running on the computer.

One noticeable dividend of the adoption and use of Automated Teller Machine (ATM) by Nigerian banks dating back to the early 1990s is the ease of access to cash by bank customers. However, incidences of ATM frauds has emerged as a limiting factor resulting in a decline adoption for transacting banking businesses. Fraudsters now employ different means to hunt for user's Personal Identification Numbers (PIN) in order to defraud unsuspecting customers.

As efforts at combating electronic mail Spam rages on, users and technocrats are becoming fuzzy in their judgment of what actually constitute Spam. Most Spam filters depend on routing information, sender addresses, message title, evidence of bulk mailing, non-solicitation and mail contents to identify Spam messages. Some researchers have posited that it is the act of blindly mass-mailing a message that makes it Spam and not the actual content of the message.

Abstract-In an age when information exchange has been made more mobile by the advent and advances in internet technology, information security is assuming a worrisome dimension. Hacking, phishing, eavesdropping, scamming and a host of other vices have become the order of the day on communication channels. This research addresses the problem of data security on multimedia systems by proposing a cascaded approach to text encryption while in transit.

The advent of wireless communication technology has brought new innovations as well as challenges to telecommunication. Consequently, the use of handheld devices such as mobile handsets, powered by the Global System for Mobile Communication (GSM) networks is on the increase. Unfortunately GSM services provisions are still faced with the challenges of inefficient bandwidth utilization and congestion in the transmission channel.

In recent years a great deal of effort has been expended to develop methods that determine the quality of speech through the use of comparative algorithms. These methods are designed to calculate an index value of quality that correlates to a mean opinion score given by human subjects in evaluation sessions. In this work, we validate PESQ (ITU-T Recommendation P. 862) and the TNO proposal (called PSQM2010) on the Perceptual Objective Listening Quality Assessment (POLQA) benchmark, which is the new ITU-T ...

In recent years a great deal of effort has been expended to develop methods that determine the quality of speech through the use of comparative algorithms. These methods are designed to calculate an index value of quality that correlates to a mean opinion score given by human subjects in evaluation sessions. In this work, we validate PESQ (ITU-T Recommendation P. 862) and the TNO proposal (called PSQM2010) on the Perceptual Objective Listening Quality Assessment (POLQA) benchmark, which is the new ITU-T ...

ABSTRACT Port sniffing, malicious hacking and the exploitation of web-based information systems’ vulnerabilities remains a clear and potent danger to communication and transactions on the world wide web. The situation is further complicated by the ubiquitous nature of the internet and the increasing volumes of private, organizational and institutional information repositories being migrated unto internet platforms. Malicious users sniffing private information engage in port scanning using automated tools hooked on proxy systems to intrude into unsuspecting hosts. Existing preventive measures that use plain-text authentication, port knocking and Single Packet Authorization (SPA) mechanism fail the requirement for strong authentication since captured tokens can be trivially replayed. They are also vulnerable to Denial of Service (DoS) attacks and a foreknowledge of the knock sequence makes it trivial for adversaries to replay the sequence in order to gain access to service ports. Our research propose a system that employ dynamic knock sequence to prevent hackers from sniffing or predicting the next sequence of interactions in online communication channels. Port knocking is combined with steganography and cryptography to make the system more robust, thus offering resilient protection against port scanners.

Scanning TCP and UDP connections for finding sucseptible hosts is one of the most popular techniques used by malicious cyber criminals and hackers to discover and map services that are listening on a specified port. Using this method an attacker can create a list of potential weaknesses and vulnerabilities in open ports leading to exploitation and compromise of a remote host. We employed port knocking sequence, steganography and cryptography as techniques of choice for the development and implementation of a scalable port knock system(SKAM) that protects knock sequence transmittion as well as services running on the network server. System performance was evaluated using standard probe tools and very promising reults were obtained.

ABSTRACT The inefficiencies of current intrusion detection system against fraudulent cyber activities attracts the attention of computer gurus, also known as “hackers” to exploit known weakness on a particular host or network. These hackers are expert programmers who mainly focus on how the Internet works, and they interact with each other to know its strengths and weaknesses. Then they develop advanced tools which an average attacker with little background can use to know the liveness, reachability and running service on the network. Once an attacker identifies these details, he can accurately launch an effective attack and get maximum benefit out of it with less probability of attack detection. In this paper, a system that opens ports on a firewall by generating a connection attempt on a set of pre-specified closed ports is established. Once a correct sequence of connection attempts is received, the firewall rules are dynamically modified to allow the host that sent the connection attempts to connect over specific port(s). This conceals and protects network services which are running on the computer.