Milad Nasr
17 papers · 2023–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (21) π Keyword Champion (3)
π€
Dynamic Duo
(10)
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(69)
π
Century Club Β· Bronze
β
The Questioner
(2)
Venues
Top co-authors
Research topics
Machine Learning
(14)
Artificial Intelligence
(9)
Application Areas
(9)
Core AI
(6)
Learning Types Β· Machine Learning
(6)
Deep Learning
(3)
Natural Language Processing
(3)
Learning Paradigms
(3)
Security & Privacy
(2)
Learning Types Β· Deep Learning
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Science
(1)
Applications
(1)
Architectures
(1)
Keywords
differential privacy
(7)
privacy auditing
(3)
privacy leakage
(3)
language model
(3)
adversarial attack
(2)
machine learning
(2)
large language model
(2)
adversarial example
(2)
gradient clipping
(2)
membership inference
(2)
knowledge distillation
(1)
model alignment
(1)
distribution shift
(1)
transfer learning
(1)
contrastive learning
(1)
privacy-preserving learning
(1)
synthetic data
(1)
loss landscape
(1)
adversarial robustness
(1)
public data
(1)
Papers
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
ICML 2025
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025
Measuring memorization in language models via probabilistic extraction
NAACL 2025
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025
Privacy Auditing of Large Language Models
ICLR 2025
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
ICLR 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
Auditing Private Prediction
ICML 2024
Query-Based Adversarial Prompt Generation
NeurIPS 2024
Stealing part of a production language model
ICML 2024
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
NAACL 2024
Are aligned neural networks adversarially aligned?
NeurIPS 2023
Effectively Using Public Data in Privacy Preserving Machine Learning
ICML 2023
Privacy Auditing with One (1) Training Run
NeurIPS 2023
Students Parrot Their Teachers: Membership Inference on Model Distillation
NeurIPS 2023
Why Is Public Pretraining Necessary for Private Model Training?
ICML 2023