Cybersecurity Commons^™

A Defensive Strategy Against Android Adversarial Malware Attacks, Fabrice Setephin Atedjio, Jean-Pierre Lienou, Frederica F. Nelson, Sachin S. Shetty, Charles A. Kamhoua

VMASC Publications

Due to the popularity of Android mobile devices over the past ten years, malicious Android applications have significantly increased. Systems utilizing machine learning techniques have been successfully applied for Android malware detection to counter the constantly changing Android malware threats. However, attackers have developed new strategies to circumvent these systems by using adversarial attacks. An attacker can carefully craft a malicious sample to deceive a classifier. Among the evasion attacks, there is the more potent one, which is based on solid optimization constraints: the Carlini-Wagner attack. Carlini-Wagner is an attack that uses margin loss, which is more efficient than cross-entropy …

Enhancing Cyber Resilience Through Traffic Generation Patterns In Complex Networks: A Study On Cascading Failures, Aymar Le Père Tchimwa Bouom, Jean-Pierre Lienou, Wilson Ejuh Geh, Frederica Nelson, Sachin Shetty, Charles Kamhoua

VMASC Publications

Network resilience is the capacity of a network to maintain and restore its fundamental operations during or after a failure. This paper investigates the resilience of communication networks with heterogeneous nodes, with host nodes that generate and receive packets and routers that only forward packets. We focus on how traffic generation patterns, defined as the distribution of data packet creation across hosts, affect network resilience. While previous studies identified optimal host placements that balance traffic loads and enhance network performance, this research explores how traffic generation patterns influence network resilience, particularly during cascading failures, where the failure of one node …

An Efficient Ddos Attack Detection Framework For Vehicular Communication, Kolandaisamy Raenu

Student Works (2020-2029)

Vehicular Ad Hoc Networks (VANETs) are rapidly gaining attention due to the diversity of services that they can potentially offer. VANET is a wireless network that allows vehicles to interconnect and communicate with other nearby vehicles and Road Side Units (RSUs). In VANET, each vehicle is considered as a node which is equipped with an On-Board Unit (OBU) and an Application Unit (AU). The nodes may connect and communicate with each other directly (i.e., Vehicle to Vehicle (V2V)) or through RSUs (i.e., Vehicle to Infrastructure (V2I)). This is primarily for alleviating an Intelligent Transport System (ITS) that aims to provide …

Adversarial Attack On Neural Machine Translation System, Abijith K. P.

Master’s Dissertations

Nowadays Deep Neural Network based solutions are deployed to solve numerous tasks. Thus, it has become absolutely important to study the robustness of these systems. Machine Translation is one of the popular applications of Deep Neural Networks. This thesis studies the robustness of Neural Machine Translation systems by generating adversarial examples with the objective to fool the model. Whenever there is a change in the source, i.e. when a word in the input sentence is replaced by an unrelated word, the translation system is supposed to reflect the changes while doing translation. These unwanted invariance learned by the model is …

Using Self-Organizing Maps For Computer Network Intrusion Detection, Manuel R. Parrachavez

Theses and Dissertations

Anomaly detection in user access patterns using artificial neural networks is a novel way of combating the ever-present concern of computer network intrusion detection for many entities around the world. Anomaly detection is a technique in network security in which a profile is built around a user's normal daily actions. The data collected for these profiles can be as following: file access attempts; failed login attempts; file creations; file access failures; and countless others. This data is collected and used as training data for a neural network.

There are many types of neural networks, such as multi-layer feed-forward network; recurrent …

The Effectiveness Of Detection Methods In Intrusion Detection Systems, Hafiz Mohd Sarim

Student Works (2000-2009)

Access control mechanisms included in operating systems are not very effective in preventing intrusions by the most determined of attackers. An Intrusion Detection System (IDS) is a security software that is able to detect an intrusion when it occurs and can potentially prevent a system compromise from being completed. The actual detection is done by the detection method used by the IDS. Four detection methods are discussed and assessed in terms of their effectiveness in repelling intrusion types, vulnerability to classification errors; and also performance in practical implementation. Recommendations are made to improve the general effectiveness of the detection methods …

Packet Sniffer & Analyzer, Khoon Kok Ong

Student Works (2000-2009)

The communication of network is a complex process which cannot be seen by human beings. Even a computer that sit on a network can only knows the conversation within itself and others computer it talk to but not others computers· conversation that it didn't take part. Furthermore, the communication in network can be viewed as traffic which always triggers a lot of unsolved problems for computers to "talk. Therefore, to solve the problems we need to exactly know what really happened inside the network traffic. A variety of sniffing tools are invented for these purpose. All of these tools have …

Enhanced Password-Based Authentication Protocol, Chee Kiam Lee

Student Works (2000-2009)

This dissertation introduces Enhanced Password-Based Authentication Protocol (E­PAP) System. E-PAP System combines asymmetric (public-key) and symmetric (secret-key) cryptography that allow two parties sharing a small shared secret to provide authentication service, exchange confidential and authenticated information over an insecure network like lntemet. E-PAP System also provides authentication service by using somelhing you know concept. It has some advantages over biometric which uses something you are concept and smancard that uses something you have concept, as it is free of equipment's physical limitations, accuracy and cost problem as well as other constraints. The core for E-PAP System is FreeSPEKE SDK, a …