Valeriia Cherepanova

profile_img_ny.jpeg

I am a postdoctoral scientist at Amazon AWS Responsible AI. Currently, I am working on problems related to safety and security of large language models. The development of LLMs introduces great capabilities, but we continue to identify new vulnerabilities and failure modes of these systems, and we still do not understand their inner workings. In my research I explore robustness of language models to out-of-domain inputs, and jailbreak attacks, detectablity of AI generated text, and biases in these models. Another area of interest to me is deep learning for tabular problems, my goal is to advance machine learning in tabular domain beyond traditional decision tree models.

Prior to joining Amazon I did my PhD at the University of Maryland, where I was advised by Prof. Tom Goldstein and worked on various topics in machine learning ranging from fairness and robustness of deep neural networks to tabular deep learning. During my PhD I did two summer internships at Amazon, in 2021 I developed NLP solution to monitor integrity and transparency of third-party Alexa Skills at Alexa Monitoring team and in 2022 I worked on improving Alexa Voice Search on FireTV at Alexa Entertainment team.

I am always looking for new collaborations, feel free to text me on LinkedIn or send me an email!

news

Jan 24, 2024 Spotting LLMs With Binoculars is now on arxiv, check our demo on huggingface!
Sep 21, 2023 A Performance-Driven Benchmark for Feature Selection got accepted to NeurIPS 23 :smiley:
Jul 27, 2023 I defended my PhD! :tada: :mortar_board:

selected publications

  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. 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
  3. Transfer learning with deep tabular models
    Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, and 5 more authors
    International Conference on Learning Representations, 2023
  4. 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
  5. 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
  6. 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