9 papers
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
Gurvan Richardeau, Gohar Dashyan, Erwan Le Merrer +1
Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt…
Token-Efficient Change Detection in LLM APIs
Timothée Chauvin, Clément Lalanne, Erwan Le Merrer +3
Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-box access to model weights or g…
Leveraging Imperfect Sources to Detect Fairwashing in Black-Box Auditing
Jade Garcia Bourrée, Erwan Le Merrer, Gilles Tredan +1
Algorithmic auditing has become central to platform accountability under frameworks such as the AI Act and the Digital Services Act. In practice, this obligation is discharged thro…
Log Probability Tracking of LLM APIs
Timothée Chauvin, Erwan Le Merrer, François Taïani +1
When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the r…
Fast In-Spectrum Graph Watermarks
Jade Garcia Bourrée, Anne-Marie Kermarrec, Erwan Le Merrer +1
We address the problem of watermarking graph objects, which consists in hiding information within them, to prove their origin. The two existing methods to watermark graphs use subg…
Robust ML Auditing using Prior Knowledge
Jade Garcia Bourrée, Augustin Godinot, Martijn De Vos +5
Among the many technical challenges to enforcing AI regulations, one crucial yet underexplored problem is the risk of audit manipulation. This manipulation occurs when a platform d…