Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
Keywords: adversarial attacks, language models, scaling laws, activation steering
TL;DR: Manipulating just 1 token’s activations in a language model can precisely dictate the subsequent generation of 100s of tokens and we demonstrate a remarkably stable, linear scaling with attack length of this control across model sizes and families
Abstract: We explore a class of adversarial attacks targeting the activations of language models to derive upper-bound scaling laws on their attack susceptibility. By manipulating a relatively small subset of model activations, $a$, we demonstrate the ability to control the exact prediction of a significant number (in some cases up to 1000) of subsequent tokens $t$. We empirically verify a scaling law where the maximum number of target tokens predicted, $t_\mathrm{max}$, depends linearly on the number of tokens $a$ whose activations the attacker controls as $t_\mathrm{max} = \kappa a$. We find that the number of bits the attacker controls on the input to exert a single bit of control on the output (a property we call \textit{attack resistance $\chi$}) is remarkably stable between $\approx 16$ and $\approx 25$ over orders of magnitude of model sizes and between model families. Compared to attacks directly on input tokens, attacks on activations are predictably much stronger, however, we identify a surprising regularity where one bit of input steered either via activations or via tokens is able to exert a surprisingly similar amount of control over the model predictions. This gives support for the hypothesis that adversarial attacks are a consequence of dimensionality mismatch between the input and output spaces. A practical implication of the ease of attacking language model activations instead of tokens is for multi-modal and selected retrieval models. By using language models as a controllable test-bed to study adversarial attacks, we explored input-output dimension regimes that are inaccessible in computer vision and greatly extended the empirical support for the dimensionality theory of adversarial attacks.
Primary Area: interpretability and explainable AI
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11563
Loading