Scholar
Maria-Irina Nicolae
Google Scholar ID: kNOsX30AAAAJ
Bosch Research, Bosch Center for AI
Citations & Impact
Citations
1,250
H-index
8
i10-index
8
Publications
20
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- *ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks.* (2025)
- *Stealix: Model Stealing via Prompt Evolution.* (ICML 2025)
- *Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment.* (AAAI 2025)
- *Stealthy Imitation: Reward-Guided Environment-Free Policy Stealing.* (ICML 2024)
- *Revisiting Neural Program Smoothing for Fuzzing.* (ESEC/FSE 2023)
- - Patents: 20+ issued US / EU / CN patents in adversarial ML, LLM security and embedded AI.
Research Experience
- - Senior Researcher — AI Security & Trust, Bosch Research, 2019 – present
- - Researcher — Adversarial AI, IBM Research, 2017 – 2019
Education
- PhD in Representation Learning, Jean Monnet University, 2013 – 2016
Background
- An AI researcher with over 10 years of experience at the intersection of AI and security. My work today centers on making AI systems more secure, robust, and trustworthy, with a focus on LLM evaluation and adversarial ML. Beyond securing AI, I have also contributed to the usage of AI in security, including ML-based fuzzing and intrusion detection.
Miscellany
- Editor of a technical blog on security, privacy, and safety called Security Garten.
