Scaling Trends in Language Model Robustness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Howe, Nikolaus, McKenzie, Ian, Hollinsworth, Oskar, Zajac, Michał, Tseng, Tom, Tucker, Aaron, Bacon, Pierre-Luc, Gleave, Adam
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916779626856448
author Howe, Nikolaus
McKenzie, Ian
Hollinsworth, Oskar
Zajac, Michał
Tseng, Tom
Tucker, Aaron
Bacon, Pierre-Luc
Gleave, Adam
author_facet Howe, Nikolaus
McKenzie, Ian
Hollinsworth, Oskar
Zajac, Michał
Tseng, Tom
Tucker, Aaron
Bacon, Pierre-Luc
Gleave, Adam
contents Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As both attack and defense gain access to more compute, and as models become larger, what happens to robustness? We argue that to answer this question requires a \emph{scaling} approach, which we employ in an extensive study of language model robustness across several classification tasks, model families, and adversarial attacks. We find that in the absence of explicit safety training, larger models are not consistently more robust; however, scale improves sample efficiency in adversarial training, though it worsens compute efficiency. Further, we find that increasing attack compute smoothly improves attack success rate against both undefended and adversarially trained models. Finally, after exploring robustness transfer across attacks and threat models, we combine attack and defense scaling rates to study the offense-defense balance. We find that while attack scaling outpaces adversarial training across all models studied, larger adversarially trained models might give defense the advantage in the long run. These results underscore the utility of the scaling lens, and provide a paradigm for evaluating future attacks and defenses on frontier models.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18213
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scaling Trends in Language Model Robustness
Howe, Nikolaus
McKenzie, Ian
Hollinsworth, Oskar
Zajac, Michał
Tseng, Tom
Tucker, Aaron
Bacon, Pierre-Luc
Gleave, Adam
Machine Learning
Artificial Intelligence
Computation and Language
Cryptography and Security
I.2.7
Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As both attack and defense gain access to more compute, and as models become larger, what happens to robustness? We argue that to answer this question requires a \emph{scaling} approach, which we employ in an extensive study of language model robustness across several classification tasks, model families, and adversarial attacks. We find that in the absence of explicit safety training, larger models are not consistently more robust; however, scale improves sample efficiency in adversarial training, though it worsens compute efficiency. Further, we find that increasing attack compute smoothly improves attack success rate against both undefended and adversarially trained models. Finally, after exploring robustness transfer across attacks and threat models, we combine attack and defense scaling rates to study the offense-defense balance. We find that while attack scaling outpaces adversarial training across all models studied, larger adversarially trained models might give defense the advantage in the long run. These results underscore the utility of the scaling lens, and provide a paradigm for evaluating future attacks and defenses on frontier models.
title Scaling Trends in Language Model Robustness
topic Machine Learning
Artificial Intelligence
Computation and Language
Cryptography and Security
I.2.7
url https://arxiv.org/abs/2407.18213