Ilia Shumailov
~Ilia_Shumailov1
12
论文总数
6.0
年均投稿
平均评分
接收情况6/12
会议分布
ICLR
8
ICML
2
NeurIPS
2
发表论文 (12 篇)
20256 篇
4
Measuring memorization in RLHF for code completion
ICLR 2025Poster
4
Interpreting the Repeated Token Phenomenon in Large Language Models
ICML 2025Poster
4
Exploring the limits of strong membership inference attacks on large language models
NeurIPS 2025Poster
3
Stealing User Prompts from Mixture-of-Experts Models
ICLR 2025Rejected
5
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
ICLR 2025Poster
4
Hardware and Software Platform Inference
ICML 2025Poster
20246 篇
4
Beyond Labeling Oracles: What does it mean to steal ML models?
ICLR 2024Rejected
4
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
ICLR 2024Rejected
4
Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
ICLR 2024Rejected
4
LLM Censorship: The Problem and its Limitations
ICLR 2024Rejected
4
Beyond Slow Signs in High-fidelity Model Extraction
NeurIPS 2024Poster
4
Human-Producible Adversarial Examples
ICLR 2024Rejected