AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

Xiangkui Cao, Jie Zhang, Meina Kan, Shiguang Shan, Xilin CHEN

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add neuron-level gradient gating (Neural Gate) to editing (ablation)MiniGPT-4 · MLLMGuard (RtA)RtA: 0.6147 -> 0.8440Improved
add neuron-level gradient gating (Neural Gate) to editing (ablation)MiniGPT-4 · PrivacyPair-test (EtA)EtA: 0.9014 -> 0.9395Improved
add gate in multi-layer editing (ablation)MiniGPT-4 · PrivacyPair-test (EtA)EtA: 0.7391 -> 0.9213Improved
remove gate in multi-layer editing (ablation)MiniGPT-4 · MLLMGuard (RtA)RtA: 0.7476 -> 0.9082Mixed
add gate in single-layer editing (ablation)LLaVA-1.5 · PrivacyPair-test (EtA)EtA: 0.9550 -> 0.9610Improved
add gate in multi-layer editing (ablation)LLaVA-1.5 · MLLMGuard (RtA)RtA: 0.7614 -> 0.8715Improved
extend editing from single to multiple layers (ablation)LLaVA-1.5 · PrivacyPair-test (EtA)EtA: 0.9610 -> 0.9823Improved
extend editing from single to multiple layers (ablation)MiniGPT-4 · PrivacyPair-test (EtA)EtA: 0.9395 -> 0.9213Hurt
apply Neural Gate instead of DINMDINM · PrivacyPair-test (EtA)EtA: 0.9312 -> 0.9395 (MiniGPT); 0.9402 -> 0.9610 (LLaVA)Improved
apply Neural Gate instead of DINMDINM · MLLMGuard (RtA)RtA: 0.7522 -> 0.8440 (MiniGPT); 0.6972 -> 0.7522 (LLaVA)Mixed
use Neural Gate vs keyword guardrail on MLLMGuard (ablation)keyword guardrail · MLLMGuard (RtA)refusal rate: 17.43% -> over 75%Improved
apply Neural Gate to modelLLaVA-1.5 · POPEaccuracy: 0.8513 -> 0.8556No clear effect

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