arXiv subjects

Diksha Goel

Publications and source records attributed to Diksha Goel.

29 records · Page 2Linked to original sources

arXiv2025

The Future of AI: Exploring the Potential of Large Concept Models

The field of Artificial Intelligence (AI) continues to drive transformative innovations, with significant progress in conversational interfaces, autonomous vehicles, and intelligent content creation. Since the launch of ChatGPT in late 2022, the rise of Generative AI has marked a pivotal era, with the term Large Language Models (LLMs) becoming a ubiquitous part of daily life. LLMs have demonstrated exceptional capabilities in tasks such as text summarization, code generation, and creative writing. However, these models are inherently limited by their token-level processing, which restricts their ability to perform abstract reasoning, conceptual understanding, and efficient generation of long-form content. To address these limitations, Meta has introduced Large Concept Models (LCMs), representing a significant shift from traditional token-based frameworks. LCMs use concepts as foundational units of understanding, enabling more sophisticated semantic reasoning and context-aware decision-making. Given the limited academic research on this emerging technology, our study aims to bridge the knowledge gap by collecting, analyzing, and synthesizing existing grey literature to provide a comprehensive understanding of LCMs. Specifically, we (i) identify and describe the features that distinguish LCMs from LLMs, (ii) explore potential applications of LCMs across multiple domains, and (iii) propose future research directions and practical strategies to advance LCM development and adoption.

cs.CL↗

arXiv2024

Detection and Prevention of Smishing Attacks

Phishing is an online identity theft technique where attackers steal users personal information, leading to financial losses for individuals and organizations. With the increasing adoption of smartphones, which provide functionalities similar to desktop computers, attackers are targeting mobile users. Smishing, a phishing attack carried out through Short Messaging Service (SMS), has become prevalent due to the widespread use of SMS-based services. It involves deceptive messages designed to extract sensitive information. Despite the growing number of smishing attacks, limited research focuses on detecting these threats. This work presents a smishing detection model using a content-based analysis approach. To address the challenge posed by slang, abbreviations, and short forms in text communication, the model normalizes these into standard forms. A machine learning classifier is employed to classify messages as smishing or ham. Experimental results demonstrate the model effectiveness, achieving classification accuracies of 97.14% for smishing and 96.12% for ham messages, with an overall accuracy of 96.20%.

cs.CR↗

arXiv2024

Discovering Top-k Structural Hole Spanners in Dynamic Networks

Structural Hole (SH) theory states that the node which acts as a connecting link among otherwise disconnected communities gets positional advantages in the network. These nodes are called Structural Hole Spanners (SHS). Numerous solutions are proposed to discover SHSs; however, most of the solutions are only applicable to static networks. Since real-world networks are dynamic networks; consequently, in this study, we aim to discover SHSs in dynamic networks. Discovering SHSs is an NP-hard problem, due to which, instead of discovering exact k SHSs, we adopt a greedy approach to discover Top-k SHSs. We first propose an efficient Tracking-SHS algorithm for updating SHSs in dynamic networks. Our algorithm reuses the information obtained during the initial runs of the static algorithm and avoids the recomputations for the nodes unaffected by the updates. Besides, motivated from the success of Graph Neural Networks (GNNs) on various graph mining problems, we also design a Graph Neural Network-based model, GNN-SHS, to discover SHSs in dynamic networks, aiming to reduce the computational cost while achieving high accuracy. We provide a theoretical analysis of the Tracking-SHS algorithm, and our theoretical results prove that for a particular type of graphs, such as Preferential Attachment graphs [1], Tracking-SHS algorithm achieves 1.6 times of speedup compared with the static algorithm. We perform extensive experiments, and our results demonstrate that the Tracking-SHS algorithm attains a minimum of 3.24 times speedup over the static algorithm. Also, the proposed second model GNN-SHS is on an average 671.6 times faster than the Tracking-SHS algorithm.

cs.SI↗

arXiv2024

Machine Learning Driven Smishing Detection Framework for Mobile Security

The increasing reliance on smartphones for communication, financial transactions, and personal data management has made them prime targets for cyberattacks, particularly smishing, a sophisticated variant of phishing conducted via SMS. Despite the growing threat, traditional detection methods often struggle with the informal and evolving nature of SMS language, which includes abbreviations, slang, and short forms. This paper presents an enhanced content-based smishing detection framework that leverages advanced text normalization techniques to improve detection accuracy. By converting nonstandard text into its standardized form, the proposed model enhances the efficacy of machine learning classifiers, particularly the Naive Bayesian classifier, in distinguishing smishing messages from legitimate ones. Our experimental results, validated on a publicly available dataset, demonstrate a detection accuracy of 96.2%, with a low False Positive Rate of 3.87% and False Negative Rate of 2.85%. This approach significantly outperforms existing methodologies, providing a robust solution to the increasingly sophisticated threat of smishing in the mobile environment.

cs.CR↗

arXiv2024

Microservice Vulnerability Analysis: A Literature Review with Empirical Insights

Microservice architectures are revolutionizing both small businesses and large corporations, igniting a new era of innovation with their exceptional advantages in maintainability, reusability, and scalability. However, these benefits come with significant security challenges, as the increased complexity of service interactions, expanded attack surfaces, and intricate dependency management introduce a new array of cybersecurity vulnerabilities. While security concerns are mounting, there is a lack of comprehensive research that integrates a review of existing knowledge with empirical analysis of microservice vulnerabilities. This study aims to fill this gap by gathering, analyzing, and synthesizing existing literature on security vulnerabilities associated with microservice architectures. Through a thorough examination of 62 studies, we identify, analyze, and report 126 security vulnerabilities inherent in microservice architectures. This comprehensive analysis enables us to (i) propose a taxonomy that categorizes microservice vulnerabilities based on the distinctive features of microservice architectures; (ii) conduct an empirical analysis by performing vulnerability scans on four diverse microservice benchmark applications using three different scanning tools to validate our taxonomy; and (iii) map our taxonomy vulnerabilities with empirically identified vulnerabilities, providing an in-depth vulnerability analysis at microservice, application, and scanning tool levels. Our study offers crucial guidelines for practitioners and researchers to advance both the state-of-the-practice and the state-of-the-art in securing microservice architectures.

cs.CR↗

arXiv2024

Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning

This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of organizational Active Directory (AD) systems. Unlike the existing literature on edge-blocking defenses which considers AD systems as static entities, our study counters this by recognizing their dynamic nature and developing advanced edge-blocking defenses through a Stackelberg game model between attacker and defender. We devise a Reinforcement Learning (RL)-based attack strategy and an RL-assisted Evolutionary Diversity Optimization-based defense strategy, where the attacker and defender improve each other strategy via parallel gameplay. To address the computational challenges of training attacker-defender strategies on numerous dynamic AD graphs, we propose an RL Training Facilitator that prunes environments and neural networks to eliminate irrelevant elements, enabling efficient and scalable training for large graphs. We extensively train the attacker strategy, as a sophisticated attacker model is essential for a robust defense. Our empirical results successfully demonstrate that our proposed approach enhances defender's proficiency in hardening dynamic AD graphs while ensuring scalability for large-scale AD.

cs.CR↗

arXiv2024

Towards Deep Learning Enabled Cybersecurity Risk Assessment for Microservice Architectures

The widespread adoption of microservice architectures has given rise to a new set of software security challenges. These challenges stem from the unique features inherent in microservices. It is important to systematically assess and address software security challenges such as software security risk assessment. However, existing approaches prove inefficient in accurately evaluating the security risks associated with microservice architectures. To address this issue, we propose CyberWise Predictor, a framework designed for predicting and assessing security risks associated with microservice architectures. Our framework employs deep learning-based natural language processing models to analyze vulnerability descriptions for predicting vulnerability metrics to assess security risks. Our experimental evaluation shows the effectiveness of CyberWise Predictor, achieving an average accuracy of 92% in automatically predicting vulnerability metrics for new vulnerabilities. Our framework and findings serve as a guide for software developers to identify and mitigate security risks in microservice architectures.

cs.SE↗

arXiv2023

Enhancing Network Resilience through Machine Learning-powered Graph Combinatorial Optimization: Applications in Cyber Defense and Information Diffusion

With the burgeoning advancements of computing and network communication technologies, network infrastructures and their application environments have become increasingly complex. Due to the increased complexity, networks are more prone to hardware faults and highly susceptible to cyber-attacks. Therefore, for rapidly growing network-centric applications, network resilience is essential to minimize the impact of attacks and to ensure that the network provides an acceptable level of services during attacks, faults or disruptions. In this regard, this thesis focuses on developing effective approaches for enhancing network resilience. Existing approaches for enhancing network resilience emphasize on determining bottleneck nodes and edges in the network and designing proactive responses to safeguard the network against attacks. However, existing solutions generally consider broader application domains and possess limited applicability when applied to specific application areas such as cyber defense and information diffusion, which are highly popular application domains among cyber attackers. This thesis aims to design effective, efficient and scalable techniques for discovering bottleneck nodes and edges in the network to enhance network resilience in cyber defense and information diffusion application domains. We first investigate a cyber defense graph optimization problem, i.e., hardening active directory systems by discovering bottleneck edges in the network. We then study the problem of identifying bottleneck structural hole spanner nodes, which are crucial for information diffusion in the network. We transform both problems into graph-combinatorial optimization problems and design machine learning based approaches for discovering bottleneck points vital for enhancing network resilience.

cs.CR↗

arXiv2023

Cost Sharing Public Project with Minimum Release Delay

We study the excludable public project model where the decision is binary (build or not build). In a classic excludable and binary public project model, an agent either consumes the project in its whole or is completely excluded. We study a setting where the mechanism can set different project release time for different agents, in the sense that high-paying agents can consume the project earlier than low-paying agents. The release delay, while hurting the social welfare, is implemented to incentivize payments to cover the project cost. The mechanism design objective is to minimize the maximum release delay and the total release delay among all agents. We first consider the setting where we know the prior distribution of the agents' types. Our objectives are minimizing the expected maximum release delay and the expected total release delay. We propose the single deadline mechanisms. We show that the optimal single deadline mechanism is asymptotically optimal for both objectives, regardless of the prior distribution. For small number of agents, we propose the sequential unanimous mechanisms by extending the largest unanimous mechanisms from [Ohseto 2000]. We propose an automated mechanism design approach via evolutionary computation to optimize within the sequential unanimous mechanisms. We next study prior-free mechanism design. We propose the group-based optimal deadline mechanism and show that it is competitive against an undominated mechanism under minor technical assumptions.

cs.GT↗

arXiv2023

Evolving Reinforcement Learning Environment to Minimize Learner's Achievable Reward: An Application on Hardening Active Directory Systems

We study a Stackelberg game between one attacker and one defender in a configurable environment. The defender picks a specific environment configuration. The attacker observes the configuration and attacks via Reinforcement Learning (RL trained against the observed environment). The defender's goal is to find the environment with minimum achievable reward for the attacker. We apply Evolutionary Diversity Optimization (EDO) to generate diverse population of environments for training. Environments with clearly high rewards are killed off and replaced by new offsprings to avoid wasting training time. Diversity not only improves training quality but also fits well with our RL scenario: RL agents tend to improve gradually, so a slightly worse environment earlier on may become better later. We demonstrate the effectiveness of our approach by focusing on a specific application, Active Directory (AD). AD is the default security management system for Windows domain networks. AD environment describes an attack graph, where nodes represent computers/accounts/etc., and edges represent accesses. The attacker aims to find the best attack path to reach the highest-privilege node. The defender can change the graph by removing a limited number of edges (revoke accesses). Our approach generates better defensive plans than the existing approach and scales better.

cs.NE↗

arXiv2023

Defending Active Directory by Combining Neural Network based Dynamic Program and Evolutionary Diversity Optimisation

Active Directory (AD) is the default security management system for Windows domain networks. We study a Stackelberg game model between one attacker and one defender on an AD attack graph. The attacker initially has access to a set of entry nodes. The attacker can expand this set by strategically exploring edges. Every edge has a detection rate and a failure rate. The attacker aims to maximize their chance of successfully reaching the destination before getting detected. The defender's task is to block a constant number of edges to decrease the attacker's chance of success. We show that the problem is #P-hard and, therefore, intractable to solve exactly. We convert the attacker's problem to an exponential sized Dynamic Program that is approximated by a Neural Network (NN). Once trained, the NN provides an efficient fitness function for the defender's Evolutionary Diversity Optimisation (EDO). The diversity emphasis on the defender's solution provides a diverse set of training samples, which improves the training accuracy of our NN for modelling the attacker. We go back and forth between NN training and EDO. Experimental results show that for R500 graph, our proposed EDO based defense is less than 1% away from the optimal defense.

cs.NE↗