pith. sign in

FatemehSadat Mireshghallah

Identifiers

  • name variant Fatemehsadat Mireshghallah 0.60 · backfill

Papers (26)

  1. LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud cs.CL · 2023 · author #5 as printed: Fatemehsadat Mireshghallah
  2. Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation cs.LG · 2023 · author #5 as printed: Fatemehsadat Mireshghallah
  3. Membership Inference Attacks against Language Models via Neighbourhood Comparison cs.CL · 2023 · author #2 as printed: Fatemehsadat Mireshghallah
  4. Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization cs.CL · 2023 · author #5 as printed: Fatemehsadat Mireshghallah
  5. Privacy-Preserving Domain Adaptation of Semantic Parsers cs.CL · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  6. Non-Parametric Temporal Adaptation for Social Media Topic Classification cs.CL · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  7. Differentially Private Model Compression cs.LG · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  8. Memorization in NLP Fine-tuning Methods cs.CL · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  9. FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations cs.LG · 2022 · author #4 as printed: Fatemehsadat Mireshghallah
  10. Mix and Match: Learning-free Controllable Text Generation using Energy Language Models cs.CL · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  11. Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks cs.LG · 2022 · author #1 as printed: Fatemehsadat Mireshghallah
  12. What Does it Mean for a Language Model to Preserve Privacy? stat.ML · 2022 · author #3 as printed: Fatemehsadat Mireshghallah
  13. UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis cs.LG · 2021 · author #1 as printed: Fatemehsadat Mireshghallah
  14. Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness cs.LG · 2021 · author #1 as printed: Fatemehsadat Mireshghallah
  15. Efficient Hyperparameter Optimization for Differentially Private Deep Learning cs.LG · 2021 · author #3 as printed: Fatemehsadat Mireshghallah
  16. Benchmarking Differential Privacy and Federated Learning for BERT Models cs.CL · 2021 · author #6 as printed: Fatemehsadat Mireshghallah
  17. When Differential Privacy Meets Interpretability: A Case Study cs.CV · 2021 · author #6 as printed: Fatemehsadat Mireshghallah
  18. DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy? cs.LG · 2021 · author #6 as printed: Fatemehsadat Mireshghallah
  19. Privacy Regularization: Joint Privacy-Utility Optimization in Language Models cs.LG · 2021 · author #1 as printed: Fatemehsadat Mireshghallah
  20. U-Noise: Learnable Noise Masks for Interpretable Image Segmentation cs.CV · 2021 · author #2 as printed: Fatemehsadat Mireshghallah
  21. Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy cs.LG · 2020 · author #2 as printed: Fatemehsadat Mireshghallah
  22. Privacy in Deep Learning: A Survey cs.LG · 2020 · author #1 as printed: Fatemehsadat Mireshghallah
  23. Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy cs.LG · 2020 · author #1 as printed: Fatemehsadat Mireshghallah
  24. WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization cs.LG · 2020 · author #3 as printed: Fatemehsadat Mireshghallah
  25. Shredder: Learning Noise Distributions to Protect Inference Privacy cs.CR · 2019 · author #1 as printed: Fatemehsadat Mireshghallah
  26. ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks cs.LG · 2018 · author #3

Mentions

  • 2309.17157 #5 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2309.11765 #5 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2305.18462 #2 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2212.10520 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2305.15008 #5 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2209.05706 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2101.05791 #2 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2203.13789 #4 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2205.12506 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2203.03929 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2106.13973 #6 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2206.01838 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2110.00135 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2203.13299 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2106.12576 #6 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2202.05520 #3 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2109.04624 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2108.03888 #3 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2106.13203 #6 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2103.07567 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2003.12154 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2004.12254 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 1905.11814 #1 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2009.06389 #2 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 2003.00146 #3 · arxiv_oai · confidence 0.70 Fatemehsadat Mireshghallah
  • 1811.01704 #3 · arxiv_oai · confidence 0.70 FatemehSadat Mireshghallah

Frequent Coauthors