Reza Shokri
19 papers · 2018–2026 · 7 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 ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (28) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(10)
🏆
Keyword Champion
(5)
⚡
Prolific Year · Productive
❓
The Questioner
(2)
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(73)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(16)
Application Areas
(12)
Artificial Intelligence
(9)
Optimization & Theory
(8)
Core AI
(7)
Natural Language Processing
(6)
Deep Learning
(4)
Resources & Methods
(4)
Learning Types
(3)
Core Methods
(2)
Learning Paradigms
(2)
Computer Science
(1)
Security & Privacy
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Keywords
membership inference
(5)
large language model
(4)
differential privacy
(4)
language model
(3)
membership inference attack
(3)
stochastic gradient descent
(2)
federated learning
(2)
privacy bound
(2)
likelihood ratio test
(2)
privacy leakage
(2)
privacy risk
(2)
renyi divergence
(1)
nonparametric model
(1)
machine learning
(1)
gaussian process
(1)
privacy attack
(1)
instruction tuning
(1)
graphical model
(1)
masked language model
(1)
representation learning
(1)
Papers
Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
EACL 2026
Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
EMNLP 2025
How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
ICLR 2025
Minerva: A Programmable Memory Test Benchmark for Language Models
ICML 2025
The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
ICML 2025
Watermark Smoothing Attacks against Language Models
EMNLP 2025
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
ICLR 2024
Leave-one-out Distinguishability in Machine Learning
ICLR 2024
Low-Cost High-Power Membership Inference Attacks
ICML 2024
Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors
EACL 2024
Bias Propagation in Federated Learning
ICLR 2023
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
NeurIPS 2023
Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning
ICLR 2023
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy
NeurIPS 2023
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
NeurIPS 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
EMNLP 2022
Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent
NeurIPS 2021
Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models
AISTATS 2021
A Non-Parametric Generative Model for Human Trajectories
IJCAI 2018