AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Steering Representations, Safeguarding Privacy: A Cross-Modal Privacy Protection Method for Generative AI

Jie Zhang, Chenxu Niu, Zhefeng Nan, Yangyan Xu, Jinta Weng

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a directional steering framework in representation space to enhance privacy protection in generative AI models across language and vision-language modalities.

Problem

Privacy protection in generative AI models that is independent of specific data and tasks, as models' privacy awareness raises new challenges.

Approach

Uses directional steering of internal representations to protect privacy, integrating with both language and vision-language models; the abstract is truncated so further specifics are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add privacy steering vector (pv)llama-2-13b-chat · Solove-Judgeaccuracy: 0.4961 -> 0.6866Improved
add privacy steering vector (pv)mistral-7b-0.1 · SALAD-Privacysafe rate: 0.6317 -> 0.8234Improved
add privacy steering vector (pv)llama-2-13b-chat · SALAD-Privacysafe rate: 0.8265 -> 0.7489Hurt
add privacy steering vector (pv)llama-2-7b-chat · Solove-Judgeaccuracy: 0.6297 -> 0.6277No clear effect
add privacy steering vector (pv)qwen-2.5-14b · MMLUaccuracy: 0.7760 -> 0.7758No clear effect
add privacy steering vector (pv)mistral-7b-0.1 · LAMBADAperplexity: 3.1818 -> 6.6412Hurt
use vector from LoRA fine-tuned model (ft pv) instead of own pv (ablation)llama-2-7b · Solove-Judgeaccuracy: 0.5452 -> 0.5717Improved
use vector from LoRA fine-tuned model (ft pv) instead of own pv (ablation)llama-3-8b · Solove-Judgeaccuracy: 0.5147 -> 0.5295Improved
use same-source base-model vector (ss pv) instead of own pv (ablation)llama-2-7b-chat · Solove-Judgeaccuracy: 0.6277 -> 0.6591Improved
use same-source base-model vector (ss pv) instead of own pv (ablation)qwen-2.5-7b-it · Solove-Judge / Confaide 2aaccuracy / score: 0.8114 and -0.663 -> 0.8330 and -37.90Improved
transfer LLM steering vector to VLM (l2v pv)llava-1.6-vicuna-7b · Ch3Efsafe choices: 12/42 -> 22/42Improved
transfer LLM steering vector to VLM (l2v pv)llava-1.6-vicuna-7b · MM-SafetyBenchsafe ratio: 0.0863 -> 0.1654Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy