Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

Dalal Alharthi; Ivan Roberto Kawaminami Garcia

cs.CRApr 5, 2026

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

Authors: Dalal Alharthi, Ivan Roberto Kawaminami Garcia

Organizations: University of Arizona, Tucson, AZ, USA

Abstract

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models (LLMs) have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic rigor. To address these dual challenges, we propose a unified, secure-by-design GenAI framework that integrates PromptShield and the Cloud Investigation Automation Framework (CIAF). PromptShield proactively defends LLMs against adversarial prompts using ontology-driven validation that standardizes user inputs and mitigates manipulation. CIAF streamlines cloud forensic investigations through structured, ontology-based reasoning across all six phases of the forensic process. We evaluate our system on real-world datasets from AWS and Microsoft Azure, demonstrating substantial improvements in both LLM security and forensic accuracy. Experimental results show PromptShield boosts classification performance under attack conditions, achieving precision, recall, and F1 scores above 93%, while CIAF enhances ransomware detection accuracy in cloud logs using Likert-transformed performance features. Our integrated framework advances the automation, interpretability, and trustworthiness of cloud forensics and LLM-based systems, offering a scalable foundation for real-time, AI-driven incident response across diverse cloud infrastructures.

Figures & tables

Figure 1: Two-part visualization of the system architecture. Part (a) demonstrates how prompt injection attacks can occur in LLM-based systems, where a malicious user manipulates input prompts to deceive the model into producing unintended responses. Part (b) introduces the PromptShield solution, an ontology-driven framework designed to validate and transform user inputs before they reach the LLM. This proactive mechanism ensures semantic consistency, mitigates injection threats, and standardizes prompts for safer and more reliable model interaction.

Figure 2: Illustration of the core components of the PromptShield ontology. It defines structured relationships among key elements such as the User Prompt, System Prompt, Model, Attributes, and Function. This formalized representation enables automated validation of prompts based on expert-defined templates and cybersecurity semantics. By embedding this ontology into the LLM workflow, PromptShield enhances interpretability and security against adversarial manipulations by ontology capabilities, such as prompt replacing.

Figure 3: Flow diagram that outlines the implementation of the proposed framework, aligning it with the six phases of cloud forensics: event identification, evidence identification, evidence collection, analysis, interpretation, and presentation. This diagram emphasizes how automation is embedded at each stage, transforming traditional manual processes into a streamlined, LLM-assisted pipeline. The figure highlights the integration of PromptShield and CIAF (Cloud Investigation Automation Framework), showcasing a cohesive and secure methodology for incident detection and investigation in cloud environments.

Figure 4: Confusion Matrix for different scenarios. a) Simple prompts are used to predict the behavior of AWS event logs. b) Results of the prompts under prompt injection attack. c) Prompt carefully pre-trained from PromptShield.

Scenario	Precision	Recall	F1 Score	Accuracy
Regular	0.75	0.8	0.76	0.79
Prompt Injection	0.64	0.51	0.24	0.29
PromptShield	0.93	0.94	0.93	0.95

Table 1: Results of proposed scenarios (Macro average)

Performance Counter	Description
Thread Count	Number of threads currently running.
% Free Space	Percentage of available disk space.
Working Set - Private	RAM used exclusively by a process.
Processor Frequency	Current CPU clock speed (MHz).
Packets Received Errors	Network packets received with errors.
Packets Outbound Errors	Network packets sent with errors.

Table 2: Monitored Azure Performance Counters and System Metrics

Figure 5: Timeline of Working Set, Working Set - Private, Committed Bytes, and Available Bytes feature behaviors.

Figure 6: Confusion matrix of a ransomware attack against an Azure virtual machine.

Class	Precision	Recall	F1-Score
Legit	0.94	0.95	0.94
Malicious	0.94	0.93	0.94
Accuracy			0.94
Macro Avg	0.94	0.94	0.94
Weighted Avg	0.94	0.94	0.94

Table 3: Classification Report

Explore similar work

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Jul 8, 2026Kiarash Ahi, Saeed ValizadehLLM Security LLMs for Cybersecurity
Virelya Intelligence Research Labs, San Francisco Bay Area, California · Google, Mountain View, California
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
Sep 9, 2026Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros +3Cybersecurity Indirect Prompt Injection
Aristotle University of Thessaloniki, Greece · Clone Systems, Cyprus
Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework
Apr 6, 2026Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen +2Structured Prompting CoT Reasoning
Department of Computing, University of Turku, 20014 Turku, Finland

Jul 8, 2026J/K move · Enter open · S save

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

Kiarash Ahi, Saeed Valizadeh

Virelya Intelligence Research Labs, San Francisco Bay Area, California · Google, Mountain View, California

LLM Security LLMs for Cybersecurity

Open paper AskPDF arXiv

Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defense and sophisticated attacks. These technologies power real-time threat detection, phishing defense, secure code generation, and vulnerability exploitation at unprecedented scales. Following a rapid surge where LLM-generated malware grew to account for an estimated 50% of detected threats by 2025, up from just 2% in 2021, navigating this highly automated threat landscape in 2026 demands next-generation security frameworks. This paper presents a comprehensive survey of the beneficial and malicious applications of LLMs in cybersecurity, including zero-day detection, DevSecOps, federated learning, synthetic content analysis, and explainable AI (XAI). Drawing on a review of over 70 academic papers, industry reports, and technical documents, this work synthesizes insights from real-world case studies across platforms like Google Play Protect, Microsoft Defender, Amazon Web Services (AWS), Apple App Store, OpenAI Plugin Stores, Hugging Face Spaces, and GitHub, alongside emerging initiatives like the SAFE Framework and AI-driven anomaly detection. We conclude with practical recommendations for responsible and transparent LLM deployment and trustworthy AI, including model watermarking, adversarial defense, and cross-industry collaboration, setting a new benchmark for rigorous, holistic cybersecurity research at the intersection of AI and threat defense, and offering a roadmap for secure, scalable LLM systems that serves as a critical reference for researchers, engineers, and security leaders navigating the complex challenges of AI-driven cybersecurity.

Abstract

Explore similar work

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework