
Hi, I'm Juan Carlos! I'm a PhD student in usable privacy and security of AI, studying how LLM-based systems collect, infer and reason about personal information, combining user studies, large-scale measurement and NLP methods.
About me
I'm a PhD student focused on the privacy and security of LLM-based conversational AI. My research studies how custom GPTs and third-party LLM apps handle personal data, how users and creators perceive their privacy risks, and how malicious conversational agents can manipulate users into revealing personal information.
Before the PhD I earned a degree in Computer Engineering and an MSc in Cybersecurity and Cyberintelligence, and spent two years at the Valencian Research Institute for Artificial Intelligence (VRAIN) building conversational chatbots and recommender systems.
When I'm not researching, I enjoy reading, listening to music and training. I also love learning new things, currently psychology, longevity and neuroscience.
Publications
- Personal Data Flows and Privacy Policy Traceability in Third-party LLM Apps in the GPT Ecosystem
Juan-Carlos Carrillo, Jose Luis Martin-Navarro, Rongjun Ma, Jose Such
PoPETs 2026 - Malicious LLM-based conversational AI makes users reveal personal information
Xiao Zhan, Juan-Carlos Carrillo, William Seymour, Jose Such
USENIX Security 2025 - Privacy Perceptions of Custom GPTs by Users and Creators
Rongjun Ma, Caterina Maidhof, Juan Carlos Carrillo, Janne Lindqvist, Jose Such
CHI 2025
My projects
Spotify Recsys
Group recommender system for Spotify that suggests songs to a group of users based on their listening history.
- Spotify API
- Sklearn
- Numpy
- JupyterNB
- Python
Twitter Echo Chamber
Collected and stored (Neo4j) the 2022 and 2023 retweets of Spanish MPs and analysed their polarization on Twitter.
- Neo4j
- Python
- Topic Modeling
- NLP
Tourism Chatbot
Conversational chatbot for the tourism sector that recommends multi-day tourist routes to users.
- RASA
- Flask
- NGINX
- AZURE
- Docker
My skills
- Python
- Flask
- NGINX
- Linux
- Pandas
- AWS
- Neo4j
- Git
- Java
- RASA
- NLP
- Transformers
- Sklearn
- Docker
- fastAPI
- Numpy
- Matplotlib
- Seaborn
- Streamlit
Experience
PhD Student
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València
Researching the privacy and security of LLM-based conversational AI and third-party LLM apps in the GPT ecosystem.
02/2024 - presentResearch & Development Technical Engineer
Valencian Research Institute for Artificial Intelligence (VRAIN)
For 2 years I worked as a technical engineer building a conversational chatbot: full-stack development, recommendation strategies, and BERT language models for tourism recommendation.
12/2021 - 09/2023MSc in Cybersecurity and Cyberintelligence
Universitat Politècnica de València
Specialized in cybersecurity and cyberintelligence, with highest honours in cyberintelligence generation.
2021-2023BSc in Computer Engineering
Universitat Politècnica de València
Studied computer engineering for 4 years. My bachelor's thesis led to my first job at the VRAIN institute.
2018-2021Contact me
Please contact me directly at juaca10j@inf.upv.es or through this form.


