Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Jinqi, Yang, Jinyu, Neiman, Tal, Fan, Lei, Yin, Bing, Tran, Son, Shah, Mubarak, Vidal, René
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917398415671296
author Luo, Jinqi
Yang, Jinyu
Neiman, Tal
Fan, Lei
Yin, Bing
Tran, Son
Shah, Mubarak
Vidal, René
author_facet Luo, Jinqi
Yang, Jinyu
Neiman, Tal
Fan, Lei
Yin, Bing
Tran, Son
Shah, Mubarak
Vidal, René
contents Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08846
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
Luo, Jinqi
Yang, Jinyu
Neiman, Tal
Fan, Lei
Yin, Bing
Tran, Son
Shah, Mubarak
Vidal, René
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.
title Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08846