Igor Shilov
Scholar

Igor Shilov

Google Scholar ID: wkAVIooAAAAJ
PhD student, Imperial College London
PrivacyMachine Learning
Google Scholar↗
Citations & Impact
All-time
Citations
748
 
H-index
7
 
i10-index
5
 
Publications
13
 
Co-authors
6
list available
Contact
No contact links provided.
Publications
10 items
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
2026
Cited
0
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
2025
Cited
0
RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
2025
Cited
0
The Tail Tells All: Estimating Model-Level Membership Inference Vulnerability Without Reference Models
2025
Cited
0
Counterfactual Influence as a Distributional Quantity
2025
Cited
0
Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
2025
Cited
0
Sub-optimal Learning in Meta-Classifier Attacks: A Study of Membership Inference on Differentially Private Location Aggregates
2024
Cited
0
Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods
arXiv.org · 2024
Cited
0
Resume (English only)
Co-authors
6 total
Ilya Mironov
Ilya Mironov
Meta
Yves-Alexandre de Montjoye
Yves-Alexandre de Montjoye
Associate Professor at Imperial College London
Alexandre Sablayrolles
Alexandre Sablayrolles
Meta AI
Matthieu Meeus
Matthieu Meeus
PhD student Compute Science, Imperial College London
Manuel Faysse
Manuel Faysse
CentraleSupélec - Université Paris Saclay
Pierre Stock
Pierre Stock
Mistral AI