The paper presents a framework that analyzes temporal traffic in applications, with a focus on statistical analysis and traffic classification. The framework utilizes time-based sampling and traffic flow selection to identify the characteristics of idle time, continuous traffic and burst threshold. It also includes time-based feature selection to improve the accuracy and efficiency of predictive models by removing irrelevant or redundant features. Our study involves exploratory data analysis and machine learning-based classification, and we found that our method improves application analysis in both statistical analysis and the precision of encrypted application traffic. We compared our approach to various state-of-the-art methods and consistently outperformed them in terms of performance. By focusing on traffic classification, our framework can benefit various domains such as Quality of Service (QoS) and security. For example, it can help network administrators identify and analyze various application characteristics, which can lead to better security measures. Overall, our approach offers a promising solution for improving temporal traffic analysis.

Honeypots are technologies aimed at thwarting adversaries by instituting attractive services that are inconsequential to the legitimate objectives of a network. Low-interaction honeypots are lightweight, but provide a limited representation of real services, while high-interaction honeypots can mimic entire systems and services, but their computational costs are expensive, and are not always viable solutions, especially in constrained environments. This work is investigating the feasibility of being able to start with a low-interaction network service and then transitioning to a high-interaction service on-the-fly. During this transition, there should be no observable distinction from the perspective of a connecting client. This paper describes ongoing work that demonstrates a basic prototype with such a capability, specifically showing that a simple Netcat listener process can dynamically transition to a full NGINX server dynamically and without severing an active TCP session.

Wireless communications networks are an integral part of intelligent systems that enhance the automation of various activities and operations embarked by humans. For example, the development of intelligent devices imbued with sensors leverages emerging technologies such as machine learning (ML) and artificial intelligence (AI), which have proven to enhance military operations through communication, control, intelligence gathering, and situational awareness. However, growing concerns in cybersecurity imply that attackers are always seeking to take advantage of the widened attack surface to launch adversarial attacks which compromise the activities of legitimate users. To address this challenge, we leverage on deep learning (DL) and the principle of cyber-deception to propose a method for defending wireless networks from the activities of jammers. Specifically, we use DL to regulate the power allocated to users and the channel they use to communicate, thereby luring jammers into attacking designated channels that are considered to guarantee maximum damage when attacked. Furthermore, by directing its energy towards the attack on a specific channel, other channels are freed up for actual transmission, ensuring secure communication. Through simulations and experiments carried out, we conclude that this approach enhances security in wireless communication systems.

In this paper, we propose a cyber deception approach using software diversity in a honeynet. Honeypot allocation is used as an active cyber deception technique to increase the uncertainty of adversaries and hide the true state of the network. Moreover, software diversity limits the ability of attackers to discover honeypots. Specifically, this paper introduces a diversity-based honeypot allocation approach for network security formulated in a game-theoretic framework. We consider a two-player zero-sum game between the network defender and the adversary. To validate our findings, we measured the potential benefits of diversity on network security and calculated the optimum diversifying strategy in Nash equilibrium using different honeypot types.

Investigating the Internet's topology is one component towards developing mechanisms that can protect the communication infrastructure underlying our critical systems and applications. We study the feasibility of capturing and fitting Internet's topology snapshots to an emulated environment called Deterlab. Physical limitations on Deterlab include the number of nodes available (i.e., about 400) and the number of interfaces (i.e., 4) to interconnect them. For example, one Internet's topology snapshot at the Autonomous Systems (AS) level has about 100 nodes with 5 nodes requiring more than 4 interfaces. In this paper, we present a short summary of the Internet's topology snapshots collected and propose a solution on how we can represent the snapshots in Deterlab and overcome the limitation of nodes requiring more than four interfaces. Preliminary results show that all paths from snapshots are maintained if a node requiring more than four interfaces had no more than four other nodes requiring four interfaces. Also, we constructed a proof of concept that captures the main idea of using then snapshots in a security experiment in Deterlab. The topology shows a Multiple Origin Autonomous System (MOAS) conflict for 10 nodes. It is scalable to larger topologies in Deterlab because we have automated the topology creation and protocol configuration.

When people speak to each other, they share a rich set of nonverbal behaviors such as varying prosody in voice. These behaviors, sometimes interpreted as demonstrations of emotions, call for appropriate responses, but today’s spoken dialog systems lack the ability to do so. We collected a corpus of persuasive dialogs, specifically conversations about graduate school between a staff member and students, and had judges label all utterances with triples indicating the perceived emotions, using the three dimensions: activation, evaluation, and power. We found immediate response patterns, in which the staff member colored her utterances in response to the emotion shown by the student in the immediately previous utterance, and built a predictive model suitable for use in a dialog system to persuasively discuss graduate school with students. Index Terms: emotional responses, dimensional emotions, user