arXiv subjects

Maanak Gupta

Publications and source records attributed to Maanak Gupta.

At least 37 records · Page 2Linked to original sources

arXiv2024

A Lightweight Edge-CNN-Transformer Model for Detecting Coordinated Cyber and Digital Twin Attacks in Cooperative Smart Farming

The agriculture sector is increasingly adopting innovative technologies to meet the growing food demands of the global population. To optimize resource utilization and minimize crop losses, farmers are joining cooperatives to share their data and resources among member farms. However, while farmers benefit from this data sharing and interconnection, it exposes them to cybersecurity threats and privacy concerns. A cyberattack on one farm can have widespread consequences, affecting the targeted farm as well as all member farms within a cooperative. In this research, we address existing gaps by proposing a novel and secure architecture for Cooperative Smart Farming (CSF). First, we highlight the role of edge-based DTs in enhancing the efficiency and resilience of agricultural operations. To validate this, we develop a test environment for CSF, implementing various cyberattacks on both the DTs and their physical counterparts using different attack vectors. We collect two smart farming network datasets to identify potential threats. After identifying these threats, we focus on preventing the transmission of malicious data from compromised farms to the central cloud server. To achieve this, we propose a CNN-Transformer-based network anomaly detection model, specifically designed for deployment at the edge. As a proof of concept, we implement this model and evaluate its performance by varying the number of encoder layers. Additionally, we apply Post-Quantization to compress the model and demonstrate the impact of compression on its performance in edge environments. Finally, we compare the model's performance with traditional machine learning approaches to assess its overall effectiveness.

cs.CR↗

arXiv2024

Explainability-Informed Targeted Malware Misclassification

In recent years, there has been a surge in malware attacks across critical infrastructures, requiring further research and development of appropriate response and remediation strategies in malware detection and classification. Several works have used machine learning models for malware classification into categories, and deep neural networks have shown promising results. However, these models have shown its vulnerabilities against intentionally crafted adversarial attacks, which yields misclassification of a malicious file. Our paper explores such adversarial vulnerabilities of neural network based malware classification system in the dynamic and online analysis environments. To evaluate our approach, we trained Feed Forward Neural Networks (FFNN) to classify malware categories based on features obtained from dynamic and online analysis environments. We use the state-of-the-art method, SHapley Additive exPlanations (SHAP), for the feature attribution for malware classification, to inform the adversarial attackers about the features with significant importance on classification decision. Using the explainability-informed features, we perform targeted misclassification adversarial white-box evasion attacks using the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks against the trained classifier. Our results demonstrated high evasion rate for some instances of attacks, showing a clear vulnerability of a malware classifier for such attacks. We offer recommendations for a balanced approach and a benchmark for much-needed future research into evasion attacks against malware classifiers, and develop more robust and trustworthy solutions.

cs.CR↗

arXiv2024

Explainability Guided Adversarial Evasion Attacks on Malware Detectors

As the focus on security of Artificial Intelligence (AI) is becoming paramount, research on crafting and inserting optimal adversarial perturbations has become increasingly critical. In the malware domain, this adversarial sample generation relies heavily on the accuracy and placement of crafted perturbation with the goal of evading a trained classifier. This work focuses on applying explainability techniques to enhance the adversarial evasion attack on a machine-learning-based Windows PE malware detector. The explainable tool identifies the regions of PE malware files that have the most significant impact on the decision-making process of a given malware detector, and therefore, the same regions can be leveraged to inject the adversarial perturbation for maximum efficiency. Profiling all the PE malware file regions based on their impact on the malware detector's decision enables the derivation of an efficient strategy for identifying the optimal location for perturbation injection. The strategy should incorporate the region's significance in influencing the malware detector's decision and the sensitivity of the PE malware file's integrity towards modifying that region. To assess the utility of explainable AI in crafting an adversarial sample of Windows PE malware, we utilize the DeepExplainer module of SHAP for determining the contribution of each region of PE malware to its detection by a CNN-based malware detector, MalConv. Furthermore, we analyzed the significance of SHAP values at a more granular level by subdividing each section of Windows PE into small subsections. We then performed an adversarial evasion attack on the subsections based on the corresponding SHAP values of the byte sequences.

cs.CR↗

arXiv2024

Explainable Deep Learning Models for Dynamic and Online Malware Classification

In recent years, there has been a significant surge in malware attacks, necessitating more advanced preventive measures and remedial strategies. While several successful AI-based malware classification approaches exist categorized into static, dynamic, or online analysis, most successful AI models lack easily interpretable decisions and explanations for their processes. Our paper aims to delve into explainable malware classification across various execution environments (such as dynamic and online), thoroughly analyzing their respective strengths, weaknesses, and commonalities. To evaluate our approach, we train Feed Forward Neural Networks (FFNN) and Convolutional Neural Networks (CNN) to classify malware based on features obtained from dynamic and online analysis environments. The feature attribution for malware classification is performed by explainability tools, SHAP, LIME and Permutation Importance. We perform a detailed evaluation of the calculated global and local explanations from the experiments, discuss limitations and, ultimately, offer recommendations for achieving a balanced approach.

cs.CR↗

arXiv2024

Specification and Enforcement of Activity Dependency Policies using XACML

The evolving smart and interconnected systems are designed to operate with minimal human intervention. Devices within these smart systems often engage in prolonged operations based on sensor data and contextual factors. Recently, an Activity-Centric Access Control (ACAC) model has been introduced to regulate these prolonged operations, referred to as activities, which undergo state changes over extended duration of time. Dependencies among different activities can influence and restrict the execution of one another, necessitating active and real-time monitoring of the dependencies between activities to prevent security violation. In the ACAC model, the activity dependencies, denoted as "D", is considered as a decision parameter for controlling a requested activity. These dependencies must be evaluated throughout all phases of an activity's life cycle. To ensure the consistency of access control rules across diverse domains and applications, a standard policy language is essential. We propose a policy framework adapting the widely-used eXtensible Access Control Markup Language (XACML) , referred to as $\mathrm{XACML_{AD}}$, to specify the activity dependency policies. This work involves extending the syntax and semantics of XACML by introducing new elements to check dependent activities' states and handle state updates on dependent activities. In addition to the language extension, we present the enforcement architecture and data flow model of evaluating policies for activity dependencies. The integration of the proposed $\mathrm{XACML_{AD}}$ policy framework and the enforcement of the policies supports dependency evaluation, necessary updates and continuous enforcement of policies to control an activity throughout its life cycle. We implement the enforcement architecture exploiting the $\mathrm{XACML_{AD}}$ policy framework and discuss the performance evaluation results.

cs.CR↗

arXiv2024

Intra-Section Code Cave Injection for Adversarial Evasion Attacks on Windows PE Malware File

Windows malware is predominantly available in cyberspace and is a prime target for deliberate adversarial evasion attacks. Although researchers have investigated the adversarial malware attack problem, a multitude of important questions remain unanswered, including (a) Are the existing techniques to inject adversarial perturbations in Windows Portable Executable (PE) malware files effective enough for evasion purposes?; (b) Does the attack process preserve the original behavior of malware?; (c) Are there unexplored approaches/locations that can be used to carry out adversarial evasion attacks on Windows PE malware?; and (d) What are the optimal locations and sizes of adversarial perturbations required to evade an ML-based malware detector without significant structural change in the PE file? To answer some of these questions, this work proposes a novel approach that injects a code cave within the section (i.e., intra-section) of Windows PE malware files to make space for adversarial perturbations. In addition, a code loader is also injected inside the PE file, which reverts adversarial malware to its original form during the execution, preserving the malware's functionality and executability. To understand the effectiveness of our approach, we injected adversarial perturbations inside the .text, .data and .rdata sections, generated using the gradient descent and Fast Gradient Sign Method (FGSM), to target the two popular CNN-based malware detectors, MalConv and MalConv2. Our experiments yielded notable results, achieving a 92.31% evasion rate with gradient descent and 96.26% with FGSM against MalConv, compared to the 16.17% evasion rate for append attacks. Similarly, when targeting MalConv2, our approach achieved a remarkable maximum evasion rate of 97.93% with gradient descent and 94.34% with FGSM, significantly surpassing the 4.01% evasion rate observed with append attacks.

cs.CR↗

arXiv2024

AbuseGPT: Abuse of Generative AI ChatBots to Create Smishing Campaigns

SMS phishing, also known as "smishing", is a growing threat that tricks users into disclosing private information or clicking into URLs with malicious content through fraudulent mobile text messages. In recent past, we have also observed a rapid advancement of conversational generative AI chatbot services (e.g., OpenAI's ChatGPT, Google's BARD), which are powered by pre-trained large language models (LLMs). These AI chatbots certainly have a lot of utilities but it is not systematically understood how they can play a role in creating threats and attacks. In this paper, we propose AbuseGPT method to show how the existing generative AI-based chatbot services can be exploited by attackers in real world to create smishing texts and eventually lead to craftier smishing campaigns. To the best of our knowledge, there is no pre-existing work that evidently shows the impacts of these generative text-based models on creating SMS phishing. Thus, we believe this study is the first of its kind to shed light on this emerging cybersecurity threat. We have found strong empirical evidences to show that attackers can exploit ethical standards in the existing generative AI-based chatbot services by crafting prompt injection attacks to create newer smishing campaigns. We also discuss some future research directions and guidelines to protect the abuse of generative AI-based services and safeguard users from smishing attacks.

cs.CR↗

arXiv2023

Automated Machine Learning for Deep Learning based Malware Detection

Deep learning (DL) has proven to be effective in detecting sophisticated malware that is constantly evolving. Even though deep learning has alleviated the feature engineering problem, finding the most optimal DL model, in terms of neural architecture search (NAS) and the model's optimal set of hyper-parameters, remains a challenge that requires domain expertise. In addition, many of the proposed state-of-the-art models are very complex and may not be the best fit for different datasets. A promising approach, known as Automated Machine Learning (AutoML), can reduce the domain expertise required to implement a custom DL model. AutoML reduces the amount of human trial-and-error involved in designing DL models, and in more recent implementations can find new model architectures with relatively low computational overhead. This work provides a comprehensive analysis and insights on using AutoML for static and online malware detection. For static, our analysis is performed on two widely used malware datasets: SOREL-20M to demonstrate efficacy on large datasets; and EMBER-2018, a smaller dataset specifically curated to hinder the performance of machine learning models. In addition, we show the effects of tuning the NAS process parameters on finding a more optimal malware detection model on these static analysis datasets. Further, we also demonstrate that AutoML is performant in online malware detection scenarios using Convolutional Neural Networks (CNNs) for cloud IaaS. We compare an AutoML technique to six existing state-of-the-art CNNs using a newly generated online malware dataset with and without other applications running in the background during malware execution.In general, our experimental results show that the performance of AutoML based static and online malware detection models are on par or even better than state-of-the-art models or hand-designed models presented in literature.

cs.CR↗

arXiv2023

The ACAC_D Model for Mutable Activity Control and Chain of Dependencies in Smart and Collaborative Systems

With the integration of connected devices, artificial intelligence, and heterogeneous networks in IoT-driven cyber-physical systems, our society is evolving as a smart, automated, and connected community. In such dynamic and distributed environments, various operations are carried out considering different contextual factors to support the automation of collaborative devices and systems. These devices often perform long-lived operations or tasks (referred to as activities) to fulfill larger goals in the collaborative environment. These activities are usually mutable (change states) and interdependent. They can influence the execution of other activities in the ecosystem, requiring active and real-time monitoring of the entire connected environment. Recently, a vision for activity-centric access control(ACAC) was proposed to enable security modeling and enforcement from the perspective and abstraction of interdependent activities. The proposed ACAC incorporates four decision parameters: Authorizations(A), oBligations(B), Conditions(C), and activity Dependencies(D) for an object agnostic access control in smart systems. In this paper, we take a step further towards maturing ACAC by focusing on activity dependencies(D) and developing a family of formal mathematically grounded models, referred to as ACAC_D. These formal models consider the real-time mutability of activities in resolving active dependencies among various activities in the ecosystem. Activity dependencies can form a chain where it is possible to have dependencies of dependencies. In ACAC, we also consider the chain of dependencies while handling the mutability of an activity. We highlight the challenges while dealing with chain of dependencies, and provide solutions to resolve these challenges. We also present a proof of concept implementation of with performance analysis for a smart farming use case.

cs.CR↗

arXiv2023

From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy

Undoubtedly, the evolution of Generative AI (GenAI) models has been the highlight of digital transformation in the year 2022. As the different GenAI models like ChatGPT and Google Bard continue to foster their complexity and capability, it's critical to understand its consequences from a cybersecurity perspective. Several instances recently have demonstrated the use of GenAI tools in both the defensive and offensive side of cybersecurity, and focusing on the social, ethical and privacy implications this technology possesses. This research paper highlights the limitations, challenges, potential risks, and opportunities of GenAI in the domain of cybersecurity and privacy. The work presents the vulnerabilities of ChatGPT, which can be exploited by malicious users to exfiltrate malicious information bypassing the ethical constraints on the model. This paper demonstrates successful example attacks like Jailbreaks, reverse psychology, and prompt injection attacks on the ChatGPT. The paper also investigates how cyber offenders can use the GenAI tools in developing cyber attacks, and explore the scenarios where ChatGPT can be used by adversaries to create social engineering attacks, phishing attacks, automated hacking, attack payload generation, malware creation, and polymorphic malware. This paper then examines defense techniques and uses GenAI tools to improve security measures, including cyber defense automation, reporting, threat intelligence, secure code generation and detection, attack identification, developing ethical guidelines, incidence response plans, and malware detection. We will also discuss the social, legal, and ethical implications of ChatGPT. In conclusion, the paper highlights open challenges and future directions to make this GenAI secure, safe, trustworthy, and ethical as the community understands its cybersecurity impacts.

cs.CR↗

arXiv2023

Analysis of Label-Flip Poisoning Attack on Machine Learning Based Malware Detector

With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward polluting the training data. Data credibility is at even higher risk with the rise of state-of-art research topics like open design principles, federated learning, and crowd-sourcing. Since the machine learning model depends on different stakeholders for obtaining data, there are no reliable automated mechanisms to verify the veracity of data from each source. Malware detection is arduous due to its malicious nature with the addition of metamorphic and polymorphic ability in the evolving samples. ML has proven to solve the zero-day malware detection problem, which is unresolved by traditional signature-based approaches. The poisoning of malware training data can allow the malware files to go undetected by the ML-based malware detectors, helping the attackers to fulfill their malicious goals. A feasibility analysis of the data poisoning threat in the malware detection domain is still lacking. Our work will focus on two major sections: training ML-based malware detectors and poisoning the training data using the label-poisoning approach. We will analyze the robustness of different machine learning models against data poisoning with varying volumes of poisoning data.

cs.CR↗

arXiv2022

Online Malware Classification with System-Wide System Calls in Cloud IaaS

Accurately classifying malware in an environment allows the creation of better response and remediation strategies by cyber analysts. However, classifying malware in a live environment is a difficult task due to the large number of system data sources. Collecting statistics from these separate sources and processing them together in a form that can be used by a machine learning model is difficult. Fortunately, all of these resources are mediated by the operating system's kernel. User programs, malware included, interacts with system resources by making requests to the kernel with system calls. Collecting these system calls provide insight to the interaction with many system resources in a single location. Feeding these system calls into a performant model such as a random forest allows fast, accurate classification in certain situations. In this paper, we evaluate the feasibility of using system call sequences for online malware classification in both low-activity and heavy-use Cloud IaaS. We collect system calls as they are received by the kernel and take n-gram sequences of calls to use as features for tree-based machine learning models. We discuss the performance of the models on baseline systems with no extra running services and systems under heavy load and the performance gap between them.

cs.CR↗

arXiv2022

Machine Learning in Access Control: A Taxonomy and Survey

An increasing body of work has recognized the importance of exploiting machine learning (ML) advancements to address the need for efficient automation in extracting access control attributes, policy mining, policy verification, access decisions, etc. In this work, we survey and summarize various ML approaches to solve different access control problems. We propose a novel taxonomy of the ML model's application in the access control domain. We highlight current limitations and open challenges such as lack of public real-world datasets, administration of ML-based access control systems, understanding a black-box ML model's decision, etc., and enumerate future research directions.

cs.CR↗

arXiv2022

BlueSky: Activity Control: A Vision for "Active" Security Models for Smart Collaborative Systems

Cyber physical ecosystem connects different intelligent devices over heterogeneous networks. Various operations are performed on smart objects to ensure efficiency and to support automation in smart environments. An Activity (defined by Gupta and Sandhu) reflects the current state of an object, which changes in response to requested operations. Due to multiple running activities on different objects, it is critical to secure collaborative systems considering run-time decisions impacted due to related activities (and other parameters) supporting active enforcement of access control decision. Recently, Gupta and Sandhu proposed Activity-Centric Access Control (ACAC) and discussed the notion of activity as a prime abstraction for access control in collaborative systems. The model provides an active security approach that considers activity decision factors such as authorizations, obligations, conditions, and dependencies among related device activities. This paper takes a step forward and presents the core components of an ACAC model and compares with other security models differentiating novel properties of ACAC. We highlight how existing models do not (or in limited scope) support `active' decision and enforcement of authorization in collaborative systems. We propose a hierarchical structure for a family of ACAC models by gradually adding the properties related to notion of activity and discuss states of an activity. We highlight the convergence of ACAC with Zero Trust tenets to reflect how ACAC supports necessary security posture of distributed and connected smart ecosystems. This paper aims to gain a better understanding of ACAC in collaborative systems supporting novel abstractions, properties and requirements.

cs.CR↗

arXiv2022

Detecting Anomalies using Overlapping Electrical Measurements in Smart Power Grids

As cyber-attacks against critical infrastructure become more frequent, it is increasingly important to be able to rapidly identify and respond to these threats. This work investigates two independent systems with overlapping electrical measurements with the goal to more rapidly identify anomalies. The independent systems include HIST, a SCADA historian, and ION, an automatic meter reading system (AMR). While prior research has explored the benefits of fusing measurements, the possibility of overlapping measurements from an existing electrical system has not been investigated. To that end, we explore the potential benefits of combining overlapping measurements both to improve the speed/accuracy of anomaly detection and to provide additional validation of the collected measurements. In this paper, we show that merging overlapping measurements provide a more holistic picture of the observed systems. By applying Dynamic Time Warping more anomalies were found -- specifically, an average of 349 times more anomalies, when considering anomalies from both overlapping measurements. When merging the overlapping measurements, a percent change of anomalies of up to 785\% can be achieved compared to a non-merge of the data as reflected by experimental results.

cs.CR↗

arXiv2022

A Survey on Adversarial Attacks for Malware Analysis

Machine learning has witnessed tremendous growth in its adoption and advancement in the last decade. The evolution of machine learning from traditional algorithms to modern deep learning architectures has shaped the way today's technology functions. Its unprecedented ability to discover knowledge/patterns from unstructured data and automate the decision-making process led to its application in wide domains. High flying machine learning arena has been recently pegged back by the introduction of adversarial attacks. Adversaries are able to modify data, maximizing the classification error of the models. The discovery of blind spots in machine learning models has been exploited by adversarial attackers by generating subtle intentional perturbations in test samples. Increasing dependency on data has paved the blueprint for ever-high incentives to camouflage machine learning models. To cope with probable catastrophic consequences in the future, continuous research is required to find vulnerabilities in form of adversarial and design remedies in systems. This survey aims at providing the encyclopedic introduction to adversarial attacks that are carried out against malware detection systems. The paper will introduce various machine learning techniques used to generate adversarial and explain the structure of target files. The survey will also model the threat posed by the adversary and followed by brief descriptions of widely accepted adversarial algorithms. Work will provide a taxonomy of adversarial evasion attacks on the basis of attack domain and adversarial generation techniques. Adversarial evasion attacks carried out against malware detectors will be discussed briefly under each taxonomical headings and compared with concomitant researches. Analyzing the current research challenges in an adversarial generation, the survey will conclude by pinpointing the open future research directions.

cs.CR↗

arXiv2021

An Ontological Knowledge Representation for Smart Agriculture

In order to provide the agricultural industry with the infrastructure it needs to take advantage of advanced technology, such as big data, the cloud, and the internet of things (IoT); smart farming is a management concept that focuses on providing the infrastructure necessary to track, monitor, automate, and analyse operations. To represent the knowledge extracted from the primary data collected is of utmost importance. An agricultural ontology framework for smart agriculture systems is presented in this study. The knowledge graph is represented as a lattice to capture and perform reasoning on spatio-temporal agricultural data.

cs.AI↗

arXiv2021

Hierarchical Federated Learning based Anomaly Detection using Digital Twins for Smart Healthcare

Internet of Medical Things (IoMT) is becoming ubiquitous with a proliferation of smart medical devices and applications used in smart hospitals, smart-home based care, and nursing homes. It utilizes smart medical devices and cloud computing services along with core Internet of Things (IoT) technologies to sense patients' vital body parameters, monitor health conditions and generate multivariate data to support just-in-time health services. Mostly, this large amount of data is analyzed in centralized servers. Anomaly Detection (AD) in a centralized healthcare ecosystem is often plagued by significant delays in response time with high performance overhead. Moreover, there are inherent privacy issues associated with sending patients' personal health data to a centralized server, which may also introduce several security threats to the AD model, such as possibility of data poisoning. To overcome these issues with centralized AD models, here we propose a Federated Learning (FL) based AD model which utilizes edge cloudlets to run AD models locally without sharing patients' data. Since existing FL approaches perform aggregation on a single server which restricts the scope of FL, in this paper, we introduce a hierarchical FL that allows aggregation at different levels enabling multi-party collaboration. We introduce a novel disease-based grouping mechanism where different AD models are grouped based on specific types of diseases. Furthermore, we develop a new Federated Time Distributed (FedTimeDis) Long Short-Term Memory (LSTM) approach to train the AD model. We present a Remote Patient Monitoring (RPM) use case to demonstrate our model, and illustrate a proof-of-concept implementation using Digital Twin (DT) and edge cloudlets.

cs.CR↗