Ali Shahin Shamsabadi
9 papers · 2020–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌍 Conference Polyglot (6) 🏃 Academic Marathon (5) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (19)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICLR (3)
EMNLP (2)
CVPR (1)
ICML (1)
NIPS (1)
UAI (1)
Top co-authors
Research topics
Keywords
large language model
(2)
privacy attack
(2)
membership inference
(2)
adversarial attack
(1)
black-box attack
(1)
relu activation
(1)
surrogate model
(1)
interpretable model
(1)
model explanation
(1)
privacy risk
(1)
black-box setting
(1)
training datum
(1)
black-box model
(1)
teacher-student model
(1)
training data extraction
(1)
model memorization
(1)
model inversion
(1)
membership privacy
(1)
memorization privacy
(1)
memorization risk
(1)
Papers
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
ICML 2025
Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
EMNLP 2025
Membership and Memorization in LLM Knowledge Distillation
EMNLP 2025
Confidential-DPproof: Confidential Proof of Differentially Private Training
ICLR 2024
Mnemonist: Locating Model Parameters that Memorize Training Examples
UAI 2023
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
ICLR 2023
A Zest of LIME: Towards Architecture-Independent Model Distances
ICLR 2022
Washing The Unwashable : On The (Im)possibility of Fairwashing Detection
NIPS 2022
ColorFool: Semantic Adversarial Colorization
CVPR 2020