3 papers
cs.LG2026
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…
cs.LG2025
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…
cs.CR2024
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…