Publications

2024

  1. Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
    Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, and 5 more authors
    arXiv preprint arXiv:2401.12070, 2024
  2. TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
    Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova, and 5 more authors
    arXiv preprint arXiv:2402.11137, 2024

2023

  1. Transfer learning with deep tabular models
    Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, and 5 more authors
    International Conference on Learning Representations, 2023
  2. A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning
    Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, and 5 more authors
    Advances in Neural Information Processing Systems, 2023
  3. A deep dive into dataset imbalance and bias in face identification
    Valeriia Cherepanova, Steven Reich, Samuel Dooley, and 4 more authors
    In Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023

2021

  1. Lowkey: Leveraging adversarial attacks to protect social media users from facial recognition
    Valeriia Cherepanova, Micah Goldblum, Harrison Foley, and 4 more authors
    International Conference on Learning Representations, 2021
  2. Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff
    Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, and 5 more authors
    In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
  3. Dp-instahide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations
    Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, and 6 more authors
    arXiv preprint arXiv:2103.02079, 2021
  4. Technical challenges for training fair neural networks
    Valeriia Cherepanova, Vedant Nanda, Micah Goldblum, and 2 more authors
    arXiv preprint arXiv:2102.06764, 2021
  5. Comparing human and machine bias in face recognition
    Samuel Dooley, Ryan Downing, George Wei, and 8 more authors
    arXiv preprint arXiv:2110.08396, 2021
  6. MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
    Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, and 3 more authors
    arXiv preprint arXiv:2106.09643, 2021

2020

  1. Unraveling meta-learning: Understanding feature representations for few-shot tasks
    Micah Goldblum, Steven Reich, Liam Fowl, and 3 more authors
    In International Conference on Machine Learning, 2020