24 citations · 28 across the 13 of their papers we have counts for
13 papers
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Alexander Panfilov, Peter Romov, Igor Shilov +3
We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injecti…
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…
RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
Roy Rinberg, Usha Bhalla, Igor Shilov +2
Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagate to related, unintended areas (…
Estimating Model-Level Membership Inference Vulnerability Without Reference Models
Euodia Dodd, Nataša Krčo, Igor Shilov +2
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…
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…
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…
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…
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…
Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods
Joseph Pollock, Igor Shilov, Euodia Dodd +1
Membership inference attacks (MIAs) are widely used to empirically assess privacy risks in machine learning models, both providing model-level vulnerability metrics and identifying…
SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)
Matthieu Meeus, Igor Shilov, Shubham Jain +3
Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In t…
Certification for Differentially Private Prediction in Gradient-Based Training
Matthew Wicker, Philip Sosnin, Igor Shilov +5
We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global…
The Mosaic Memory of Large Language Models
Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye
As Large Language Models (LLMs) become widely adopted, understanding how they learn from, and memorize, training data becomes crucial. Memorization in LLMs is widely assumed to onl…
Copyright Traps for Large Language Models
Matthieu Meeus, Igor Shilov, Manuel Faysse +1
Questions of fair use of copyright-protected content to train Large Language Models (LLMs) are being actively debated. Document-level inference has been proposed as a new task: inf…