Milad Nasr
17 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5)
🌈
Renaissance Researcher
(5)
🌍
Conference Polyglot
(4)
🤝
Dynamic Duo
(10)
💎
Century Club
(17)
⚡
Prolific Year
(8)
❓
The Questioner
(2)
Conferences
ICML (6)
ICLR (5)
NIPS (4)
NAACL (2)
Top co-authors
Research topics
Keywords
differential privacy
(4)
adversarial example
(2)
machine learning
(2)
language model
(2)
knowledge distillation
(1)
model distillation
(1)
loss landscape
(1)
privacy-preserving learning
(1)
deep retrieval system
(1)
distribution shift
(1)
adversarial attack
(1)
adversarial perturbation
(1)
model training
(1)
public datum
(1)
statistical generalization
(1)
synthetic datum
(1)
gradient clipping
(1)
privacy auditing
(1)
privacy attack
(1)
adversarial prompt
(1)
Papers
Measuring memorization in language models via probabilistic extraction
NAACL 2025
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
ICLR 2025
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025
Privacy Auditing of Large Language Models
ICLR 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
ICML 2025
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
NAACL 2024
Query-Based Adversarial Prompt Generation
NIPS 2024
Stealing part of a production language model
ICML 2024
Auditing Private Prediction
ICML 2024
Students Parrot Their Teachers: Membership Inference on Model Distillation
NIPS 2023
Effectively Using Public Data in Privacy Preserving Machine Learning
ICML 2023
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023
Privacy Auditing with One (1) Training Run
NIPS 2023
Are aligned neural networks adversarially aligned?
NIPS 2023