← Authors

David Evans

20 papers · 2003–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (41) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (22) πŸ’Ž Century Club (20) ❓ The Questioner (2) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (89)

Conferences

EMNLP (4) NIPS (4) ICLR (3) NAACL (3) ICML (2) ACL (1) AISTATS (1) CVPR (1) UAI (1)

Top co-authors

Xiao Zhang (7) Yangfeng Ji (6) Hannah Chen (4) Fnu Suya (3) Quanquan Gu (3) Saeed Mahloujifar (2) Anshuman Suri (2) Tianhao Wang (2) Hannah Cyberey (2) Lingxiao Wang (2)

Research topics

Privacy (2) Differential Privacy (1)

Keywords

differential privacy (3) adversarial example (3) adversarial attack (3) poisoning attack (2) adversarial robustness (2) large language model (2) gender bia (2) natural language inference (2) intrinsic robustness (2) adversarial learning (2) paraphrase identification (2) nonconvex optimization (1) image classification (1) online learning (1) model selection (1) representation learning (1) unsupervised learning (1) graph theory (1) stochastic gradient descent (1) causal inference (1)

Papers

Unsupervised Concept Vector Extraction for Bias Control in LLMs EMNLP 2025
Do Prevalent Bias Metrics Capture Allocational Harms from LLMs? NAACL 2025
Addressing Both Statistical and Causal Gender Fairness in NLP Models NAACL 2024
Manipulating Transfer Learning for Property Inference CVPR 2023
Efficient Privacy-Preserving Stochastic Nonconvex Optimization UAI 2023
GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces NIPS 2023
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners? NIPS 2023
Understanding Intrinsic Robustness Using Label Uncertainty ICLR 2022
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models EMNLP 2022
Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces ICLR 2021
Model-Targeted Poisoning Attacks with Provable Convergence ICML 2021
Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory EMNLP 2020
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models AISTATS 2020
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization ICML 2020
Pointwise Paraphrase Appraisal is Potentially Problematic ACL 2020
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness NIPS 2019
Cost-Sensitive Robustness against Adversarial Examples ICLR 2019
Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization NIPS 2018
Columbia’s Newsblaster: New Features and Future Directions NAACL 2003