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