activity
20222025
most citedAutoregressive Perturbations for Data Poisoning

8 citations · 13 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2025★ 1 cited

Identifying and Evaluating Inactive Heads in Pretrained LLMs

Pedro Sandoval-Segura, Xijun Wang, Ashwinee Panda +4

Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks,…

cs.CV2023

A Simple and Efficient Baseline for Data Attribution on Images

Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum +2

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs duri…

cs.LG2023★ 1 cited

What Can We Learn from Unlearnable Datasets?

Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping +2

In an era of widespread web scraping, unlearnable dataset methods have the potential to protect data privacy by preventing deep neural networks from generalizing. But in addition t…

cs.LG2023★ 1 cited

JPEG Compressed Images Can Bypass Protections Against AI Editing

Pedro Sandoval-Segura, Jonas Geiping, Tom Goldstein

Recently developed text-to-image diffusion models make it easy to edit or create high-quality images. Their ease of use has raised concerns about the potential for malicious editin…

cs.LG2022★ 8 cited

Autoregressive Perturbations for Data Poisoning

Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping +3

The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been pro…

cs.LG2022★ 2 cited

Poisons that are learned faster are more effective

Pedro Sandoval-Segura, Vasu Singla, Liam Fowl +4

Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical us…