Cover Image

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hossain, Ismail, Puppala, Sai, Ferdaus, Jannatul, Alam, Md Jahangir, Lee, Yoonpyo, Alam, Syed Bahauddin, Talukder, Sajedul
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
by: Puppala, Sai, et al.
Published: (2026)

Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
by: Ahad, Tanzim, et al.
Published: (2026)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
by: Hossain, Ismail, et al.
Published: (2026)

AI-in-the-Loop: Privacy Preserving Real-Time Scam Detection and Conversational Scambaiting by Leveraging LLMs and Federated Learning
by: Hossain, Ismail, et al.
Published: (2025)

Generative AI like ChatGPT in Blockchain Federated Learning: use cases, opportunities and future
by: Puppala, Sai, et al.
Published: (2024)

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
by: Hossain, Ismail, et al.
Published: (2026)

EVOLVE: Predicting User Evolution and Network Dynamics in Social Media Using Fine-Tuned GPT-like Model
by: Hossain, Ismail, et al.
Published: (2024)

SCALE: Self-regulated Clustered federAted LEarning in a Homogeneous Environment
by: Puppala, Sai, et al.
Published: (2024)

FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG
by: Puppala, Sai, et al.
Published: (2024)

Comprehensive Privacy Risk Assessment in Social Networks Using User Attributes Social Graphs and Text Analysis
by: Alam, Md Jahangir, et al.
Published: (2025)

SocFedGPT: Federated GPT-based Adaptive Content Filtering System Leveraging User Interactions in Social Networks
by: Puppala, Sai, et al.
Published: (2024)

Variational Gaussian Mixture Manifold Models for Client-Specific Federated Personalization
by: Puppala, Sai, et al.
Published: (2025)

Real-Time Personalized Content Adaptation through Matrix Factorization and Context-Aware Federated Learning
by: Puppala, Sai, et al.
Published: (2025)

SocialRec: User Activity Based Post Weighted Dynamic Personalized Post Recommendation System in Social Media
by: Hossain, Ismail, et al.
Published: (2024)

EVOLVE-X: Embedding Fusion and Language Prompting for User Evolution Forecasting on Social Media
by: Hossain, Ismail, et al.
Published: (2025)

Optimus-Q: Utilizing Federated Learning in Adaptive Robots for Intelligent Nuclear Power Plant Operations through Quantum Cryptography
by: Puppala, Sai, et al.
Published: (2025)

LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
by: Haque, Md Ahsanul, et al.
Published: (2025)

LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning
by: Puppala, Sai, et al.
Published: (2025)

Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
by: Roy, Samrendra, et al.
Published: (2026)

Hiding Information for Secure and Covert Data Storage in Commercial ReRAM Chips
by: Ferdaus, Farah, et al.
Published: (2024)

Distributed Threat Intelligence at the Edge Devices: A Large Language Model-Driven Approach
by: Hasan, Syed Mhamudul, et al.
Published: (2024)

Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems
by: Roy, Samrendra, et al.
Published: (2026)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
by: Asif, Sadia, et al.
Published: (2026)

PhishGuard: A Multi-Layered Ensemble Model for Optimal Phishing Website Detection
by: Ovi, Md Sultanul Islam, et al.
Published: (2024)

Assessing the influence of cybersecurity threats and risks on the adoption and growth of digital banking: a systematic literature review
by: Waliullah, Md., et al.
Published: (2025)

Cybersecurity: Past, Present and Future
by: Alam, Shahid
Published: (2022)

Optimizing DDoS Detection in SDNs Through Machine Learning Models
by: Haque, Md. Ehsanul, et al.
Published: (2025)

AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration
by: Chen, Jizhou, et al.
Published: (2025)

IoTWarden: A Deep Reinforcement Learning Based Real-time Defense System to Mitigate Trigger-action IoT Attacks
by: Alam, Md Morshed, et al.
Published: (2024)

Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities
by: Alam, Md Tauseef, et al.
Published: (2024)

Privacy-Aware Machine Unlearning with SISA for Reinforcement Learning-Based Ransomware Detection
by: Ferdous, Jannatul, et al.
Published: (2026)

Quantum-Edge Cloud Computing: A Future Paradigm for IoT Applications
by: Hossain, Mohammad Ikbal, et al.
Published: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
by: Guo, Jiahe, et al.
Published: (2026)

Enhancing Smart Contract Vulnerability Detection in DApps Leveraging Fine-Tuned LLM
by: Bu, Jiuyang, et al.
Published: (2025)

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
by: Hasan, Md. Mehedi, et al.
Published: (2025)

AgenticVM: Agentic AI for Adaptive Software Vulnerability Management
by: Arifin, Asrul, et al.
Published: (2026)

PoseGuard: Pose-Guided Generation with Safety Guardrails
by: Wang, Kongxin, et al.
Published: (2025)

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
by: Li, Junchen, et al.
Published: (2026)

KingsGuard: Enclave Data Protection Under Real-World TEE Vulnerabilities
by: Allaqband, Saltanat Firdous, et al.
Published: (2026)

TL-RL-FusionNet: An Adaptive and Efficient Reinforcement Learning-Driven Transfer Learning Framework for Detecting Evolving Ransomware Threats
by: Ferdous, Jannatul, et al.
Published: (2026)