2 citations · 2 across the 2 of their papers we have counts for
3 papers
Genesis Steering: Better Activation Steering Through Training Data
Tora Bodin, Eric Aubinais, Ilaria Torre +1
Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a…
Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study
Eric Aubinais, Philippe Formont, Pablo Piantanida +1
Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance levels comparable to those of the origina…
Fundamental Limits of Membership Inference Attacks on Machine Learning Models
Eric Aubinais, Elisabeth Gassiat, Pablo Piantanida
Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This a…