AIConfPaper
← Search

Valeriia Cherepanova

7 accepted papers

2024

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum +2
ICML 2024poster

Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-g…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2024

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks

Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum +2
NeurIPS 2024poster

While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to large language models, PFNs make use of pretraining and in-context learning to achieve strong performance on new tasks i…

Cited by 26Source ↗PDF ↗Scholar ↗
2023

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning

Valeriia Cherepanova, Roman Levin, Gowthami Somepalli, Jonas Geiping, C. Bayan Bruss, Andrew Gordon Wilson +2
NeurIPS 2023poster

Academic tabular benchmarks often contain small sets of curated features. In contrast, data scientists typically collect as many features as possible into their datasets, and even engineer new features from existing ones. To prevent over-fitting in subsequent downstream modeling, practitioners commo…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2023

Transfer Learning with Deep Tabular Models

Roman Levin, Valeriia Cherepanova, Avi Schwarzschild, Arpit Bansal, C. Bayan Bruss, Tom Goldstein +2
ICLR 2023poster

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models is that they are easily fine-tuned in new domains and learn…

Cited by 48Source ↗PDF ↗code ↗Scholar ↗
2021

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John P Dickerson, Gavin Taylor +1
ICLR 2021poster

Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been pr…

Cited by 163Source ↗PDF ↗Scholar ↗
2021

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff

Eitan Borgnia, Valeriia Cherepanova, Liam Fowl, Amin Ghiasi, Jonas Geiping, Micah Goldblum +2
ICASSP 2021accepted

Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals revealed heightened fear in the private sector regarding data poisoning. Many previous defenses against poisoning either fai…

Cited by 0Source ↗Scholar ↗
2020

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

Micah Goldblum, Steven Reich, Liam Fowl, Renkun Ni, Valeriia Cherepanova, Tom Goldstein
ICML 2020poster

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the und…

Cited by 90Source ↗PDF ↗code ↗Scholar ↗