[2604.03912] Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

[2604.03912] Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

arXiv - AI 4 min read

About this article

Abstract page for arXiv paper 2604.03912: Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

Computer Science > Cryptography and Security arXiv:2604.03912 (cs) [Submitted on 5 Apr 2026] Title:Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework Authors:Dalal Alharthi, Ivan Roberto Kawaminami Garcia View a PDF of the paper titled Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework, by Dalal Alharthi and 1 other authors View PDF HTML (experimental) 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 precisio...

Originally published on April 07, 2026. Curated by AI News.

Related Articles

[2603.07475] A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
Llms

[2603.07475] A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs

Abstract page for arXiv paper 2603.07475: A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs

arXiv - Machine Learning · 3 min ·
[2601.22925] BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
Llms

[2601.22925] BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models

Abstract page for arXiv paper 2601.22925: BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models

arXiv - Machine Learning · 4 min ·
[2512.10551] LLM-Auction: Generative Auction towards LLM-Native Advertising
Llms

[2512.10551] LLM-Auction: Generative Auction towards LLM-Native Advertising

Abstract page for arXiv paper 2512.10551: LLM-Auction: Generative Auction towards LLM-Native Advertising

arXiv - Machine Learning · 3 min ·
[2511.17411] SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
Llms

[2511.17411] SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding

Abstract page for arXiv paper 2511.17411: SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding

arXiv - Machine Learning · 4 min ·
More in Llms: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime