RESEARCHER PROFILE
Mohammadreza Rashidi
← Back to University of Applied Sciences Europe
M
University of Applied Sciences Europe
Mohammadreza Rashidi works in Adversarial Robustness in Machine Learning, Security and Verification in Computing, Web Application Security Vulnerabilities, Network Security and Intrusion Detection, Information and Cyber Security. Recorded institutional associations include University of Applied Sciences Europe.
22Publications
0Citations
0H-index
Inclusion identifies researchers whose recorded research contributions may inform their university’s understanding of its research community. It does not rank individual research quality or establish current employment.
Selected research works
Up to 100 highly cited works; DOI links open the original research. Counts reflect the collected record, not real-time citation totals.
Pi-hole Attack Surface
2025 · 0 citationsRed Teamer Gadgets
2025 · 0 citationsThe Art of Post-Exploitation
2025 · 0 citationsComprehensive Mimikatz Ebook: A Practical Guide to Post-Exploitation
2025 · 0 citationsFrom WEP to WPA3: A Red Teamer’s Guide to Wi-Fi Exploitation Techniques
2025 · 0 citationsDeepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks
2026 · 0 citationsBenchmarking and Stress-Testing Off-the-Shelf Vision Embeddings for Surface Re-Identification in Open-Source Intelligence
2026 · 0 citationsCode and scripts for "Benchmarking and Stress-Testing Off-the-Shelf Vision Embeddings for Surface Re-Identification in Open-Source Intelligence"
2026 · 0 citationsMeasuring How LLM Tool Descriptions, Cross-Tool Ambiguity, and Action Chains Compose into Excessive Agency Exploits
2026 · 0 citationsThe Claim-to-Action Gap: Measuring How Misinformation Turns False State into Tool Calls in Tool-Using LLM Agents
2026 · 0 citationsLabelled-Metadata Channels and Declarative Payload Phrasing in Hidden Prompt Injection: A Cross-Format Measurement Study
2026 · 0 citationsTyped-Field Forgery in Agent Communication Protocol Await-Resume: A Study of Content, Metadata, and Encoding Sub-Channels as Injection Vectors
2026 · 0 citationsNaive Judges Fabricate the Extraction: A Read-the-Transcript Cross-Vendor Study of Ten Working and Ten Failing LLM Secret-Extraction Framings
2026 · 0 citationsNormalization Is Necessary but Insufficient: A Cross-Class Audit of Glyph-Level Obfuscation and Attributive Reframing Against LLM Content-Safety Guards
2026 · 0 citationsContext-accumulation Attacks on Language-model Confidentiality Boundaries: Turns-to-Breach, the Primacy of Mechanism over Context Length, and the Leak-while-refusing Failure Mode
2026 · 0 citationsReasoning-Tier Drift in RL-Aligned LLMs: Within-Family Safety Spread Across Six Gemini Tiers on a Harm-Free Insult-Reproduction Protocol
2026 · 0 citationsLabel-Free but Signal-Free: Measuring the Failure of Unsupervised Actor Anomaly Detection Against a Deterministic Ownership Join for IDOR
2026 · 0 citationsThe Encoding Alphabet Is the Security Boundary: Measuring the Coverage Limits of Deterministic Multi-Encoding Decoding Against Cross-Stage Instruction Laundering in LLM Agent Pipelines
2026 · 0 citationsPassive Detection of Broken Object-Level Authorization by Joining Access, Authentication, and Ownership Telemetry into Synthesized Violation Labels
2026 · 0 citationsIndistinguishable by Frequency: Measuring the Separation Failure of Surprisal and Count-Outlier Anomaly Detection on Real Web-Server Logs
2026 · 0 citationsContent in Graph Clothing: Structural Link Prediction Does Not Beat a Text Baseline for Weakness Classification of Vulnerability Reports
2026 · 0 citationsAutoGen guard placement: probe set, source snapshots and run logs
2026 · 0 citations
