most citedWatermarking Training Data of Music Generation Models

2 citations · 2 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

Igor Shilov, Alex Cloud, Aryo Pradipta Gema +5

Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenge…

cs.LG2025

The Tail Tells All: Estimating Model-Level Membership Inference Vulnerability Without Reference Models

Euodia Dodd, Nataša Krčo, Igor Shilov +1

Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attacks require training numerous, of…

cs.LG2025

Counterfactual Influence as a Distributional Quantity

Matthieu Meeus, Igor Shilov, Georgios Kaissis +1

Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metri…

cs.CR2025

Exploring the limits of strong membership inference attacks on large language models

Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo +13

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language mode…

cs.CR2024

Sub-optimal Learning in Meta-Classifier Attacks: A Study of Membership Inference on Differentially Private Location Aggregates

Yuhan Liu, Florent Guepin, Igor Shilov +1

The widespread collection and sharing of location data, even in aggregated form, raises major privacy concerns. Previous studies used meta-classifier-based membership inference att…

cs.LG20242 cited

Watermarking Training Data of Music Generation Models

Pascal Epple, Igor Shilov, Bozhidar Stevanoski +1

Generative Artificial Intelligence (Gen-AI) models are increasingly used to produce content across domains, including text, images, and audio. While these models represent a major…