Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Zhiyuan, Abaimov, Stanislav, Gardiner, Joseph, Belguith, Sana
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908668931342336
author Xu, Zhiyuan
Abaimov, Stanislav
Gardiner, Joseph
Belguith, Sana
author_facet Xu, Zhiyuan
Abaimov, Stanislav
Gardiner, Joseph
Belguith, Sana
contents Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a vulnerable attack surface for behavioral control. Building on recent findings on attention sinks and compression valleys, we identify a high-gain region in the residual stream where small, well-aligned perturbations are causally amplified along the autoregressive trajectory--a Causal Amplification Effect (CAE). We exploit this as an attack surface via Sensitivity-Scaled Steering (SSS), a progressive activation-level attack that combines beginning-of-sequence (BOS) anchoring with sensitivity-based reinforcement to focus a limited perturbation budget on the most vulnerable layers and tokens. We show that across multiple open-weight models and four behavioral axes, SSS induces large shifts in evil, hallucination, sycophancy, and sentiment while preserving high coherence and general capabilities, turning activation steering into a concrete security concern for white-box and supply-chain LLM deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17194
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
Xu, Zhiyuan
Abaimov, Stanislav
Gardiner, Joseph
Belguith, Sana
Cryptography and Security
Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a vulnerable attack surface for behavioral control. Building on recent findings on attention sinks and compression valleys, we identify a high-gain region in the residual stream where small, well-aligned perturbations are causally amplified along the autoregressive trajectory--a Causal Amplification Effect (CAE). We exploit this as an attack surface via Sensitivity-Scaled Steering (SSS), a progressive activation-level attack that combines beginning-of-sequence (BOS) anchoring with sensitivity-based reinforcement to focus a limited perturbation budget on the most vulnerable layers and tokens. We show that across multiple open-weight models and four behavioral axes, SSS induces large shifts in evil, hallucination, sycophancy, and sentiment while preserving high coherence and general capabilities, turning activation steering into a concrete security concern for white-box and supply-chain LLM deployments.
title Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
topic Cryptography and Security
url https://arxiv.org/abs/2511.17194