Ilia Shumailov
13 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (13) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🌈 Renaissance Researcher (6)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
⚡
Prolific Year
(6)
❓
The Questioner
(2)
🔥
Unstoppable
(5)
💎
Century Club
(13)
Conferences
ICML (6)
ICLR (2)
ACL (1)
CVPR (1)
EMNLP (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
adversarial attack
(3)
adversarial machine learning
(2)
large language model
(2)
neural network
(2)
neural network security
(2)
prompt engineering
(1)
model architecture
(1)
parameter optimization
(1)
backdoor attack
(1)
black-box attack
(1)
memory efficiency
(1)
inductive bia
(1)
language model
(1)
inference optimization
(1)
weight extraction
(1)
training datum
(1)
image manipulation
(1)
watermark removal
(1)
model extraction
(1)
data memorization
(1)
Papers
Interpreting the Repeated Token Phenomenon in Large Language Models
ICML 2025
Measuring memorization in language models via probabilistic extraction
NAACL 2025
Position: Machine Learning Models Have a Supply Chain Problem
ICML 2025
Hardware and Software Platform Inference
ICML 2025
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
ICLR 2025
Measuring memorization in RLHF for code completion
ICLR 2025
Beyond Slow Signs in High-fidelity Model Extraction
NIPS 2024
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
ICML 2024
Revisiting Automated Prompting: Are We Actually Doing Better?
ACL 2023
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
EMNLP 2023
Architectural Backdoors in Neural Networks
CVPR 2023
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
ICML 2022
Markpainting: Adversarial Machine Learning meets Inpainting
ICML 2021