4 papers
PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents
Lucas Biechy, Cédric Eichler, Héber H. Arcolezi +1
While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources. We intro…
Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models
Lucas Biechy, Cédric Eichler, Adrien Boiret +1
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In production environments, where lo…
Onto-DP: Constructing Neighborhoods for Differential Privacy on Ontological Databases
Yasmine Hayder, Adrien Boiret, Cédric Eichler +1
In this paper, we investigate how attackers can discover sensitive information embedded within databases by exploiting inference rules. We demonstrate the inadequacy of naively app…
Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
Yanming Li, Cédric Eichler, Nicolas Anciaux +3
We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our meth…