Helmut Neukirchen

.- AI Vulnerabilities..- How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference..- MEEA: Mere Exposure Effect-Driven Confrontational Optimization for LLM Jailbreaking..- Exposing Vulnerabilities in AI-Based Malware Detectors: Adversarial, Backdoor, and Poisoning Attacks..- Detecting and Analysing GenAI Output..- FreDA: Training-Free Test-Time Adaptation for Deepfake Detection via Non-Parametric Cache Retrieval..- A Multi-stage Framework for Detection and Attribution of LLM-generated Text..- MARS: LLM Toxicity Mitigation via Multi-Dimensional Adaptive Representation Steering..- AI-Enhanced Investigations..- Multimodal Online Black Industry Discovery with Long-Context Compression..- Agentic AI Enhanced Security Workflow for Explainable Host-Based Intrusion Detection..- A methodology for producing recursive medical forensic image analysis responses using VLMs.- Critical Infrastructure Resilience..- Unsupervised Detection of False Data Injection Attacks in Nuclear Radiation Dose Time Series Using Generative Models..- Quantifying Cyber Attack Impact on UAV-Based Nuclear Containment Inspection: A Forensic-Ready Simulation Framework..- R-FIGM: A Real-Time Forensic Intelligence Governance Model for Cyber Crisis Management in Critical Infrastructure..- Cryptography and Steganography..- RENet-Crypt: An Novel Image Encryption Method Based on Chaotic Systems...