22 citations · 28 across the 4 of their papers we have counts for
4 papers
Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains
Roy Rinberg, Annabelle Michael Carrell, Simon Henniger +2
We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of mo…
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
Nicholas Carlini, Jorge Chávez-Saab, Anna Hambitzer +2
Deep neural networks (DNNs) are valuable assets, yet their public accessibility raises security concerns about parameter extraction by malicious actors. Recent work by Carlini et a…
Poisoning the Unlabeled Dataset of Semi-Supervised Learning
Nicholas Carlini
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach w…