FatemehSadat Mireshghallah
12 papers · 2021–2024 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (25) 🏆 Keyword Champion (2)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(56)
Top co-authors
Research topics
Machine Learning
(12)
Application Areas
(10)
Artificial Intelligence
(8)
Natural Language Processing
(8)
Core AI
(6)
Deep Learning
(5)
Generation
(4)
Learning Types · Machine Learning
(4)
Security & Privacy
(3)
Learning Types · Deep Learning
(3)
Privacy
(3)
Resources & Methods
(3)
Applications
(2)
Learning Paradigms
(2)
Models
(2)
Keywords
differential privacy
(5)
language model
(4)
membership inference
(3)
privacy risk
(3)
text generation
(2)
large language model
(2)
energy-based model
(2)
synthetic data generation
(2)
few-shot learning
(2)
metropolis-hastings sampling
(2)
membership inference attack
(2)
masked language model
(1)
natural language processing
(1)
task-oriented dialogue
(1)
semantic parsing
(1)
sentiment analysis
(1)
in-context learning
(1)
adversarial attack
(1)
domain adaptation
(1)
false positive rate
(1)
Papers
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
ICLR 2024
A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation
CoNLL 2023
Membership Inference Attacks against Language Models via Neighbourhood Comparison
ACL 2023
Privacy-Preserving Domain Adaptation of Semantic Parsers
ACL 2023
Privacy-Preserving Natural Language Processing
EACL 2023
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models
EMNLP 2022
Differentially Private Model Compression
NeurIPS 2022
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models
ACL 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
EMNLP 2022
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
NAACL 2022
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
NAACL 2021
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness
EMNLP 2021