AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Co-Steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs

Jingmin Zhu, Rollin Omari, Tamas Abraham, Junae Kim, Amardeep Kaur, Trung Le, Dinh Q Phung, Qiuhong Ke

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 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 steering alignment loss with coordinated alternating optimization (vs independent optimization) (ablation)Co-Steer · MM-SafetyBenchASR (%): 79.62 -> 87.20 (InternVL2); 78.19 -> 84.65 (Qwen2-VL); 86.85 -> 88.94 (MiniGPT-4)Improved
combine visual and textual perturbations rather than a single modality (ablation)Co-Steer · MM-SafetyBenchASR (%): 55.28 -> 79.62 (InternVL2, visual-only vs independent)Improved
extract steering vector with SVD instead of cross-modal mean (ablation)Co-Steer · MM-SafetyBenchASR (%): 84.58 -> 87.20 (InternVL2); 82.19 -> 84.65 (Qwen2-VL); 86.47 -> 88.94 (MiniGPT-4)Improved
use both modalities when building the steering vector instead of single-modality averaging (ablation)Co-Steer · MM-SafetyBenchASR (%): 62.34 / 68.72 -> 84.58 (InternVL2)Improved
steer at middle fusion layer 15 rather than early or late layers (ablation)Co-Steer · MM-SafetyBench (InternVL2-8B)ASR (%): 62.34 (L3) / 68.47 (L25) -> 87.20 (L15)Improved
increase SVD sample pairs from 10 to 100 (ablation)Co-Steer · MM-SafetyBench (InternVL2-8B)ASR (%): 76.54 -> 87.20Improved
increase SVD pairs beyond 100 (150, 200) (ablation)Co-Steer · MM-SafetyBench (InternVL2-8B)ASR (%): 87.20 -> 87.58No clear effect
set coupling weight lambda to 1.0-1.5 vs lambda=0 or 2.0 (ablation)Co-Steer · MM-SafetyBenchASR (%)Improved
widen steering-loss layer window from 1 to 3 or 5 layers (ablation)Co-Steer · MM-SafetyBench (Qwen2-VL-7B)ASR (%): 84.65 -> 86.43 (width 3); 83.39 (width 5)Mixed
reduce visual budget from eps 32/255 to 16/255 (ablation)Co-Steer · MM-SafetyBenchASR (%): 84.65 -> 80.89 (Qwen2-VL); 87.20 -> 85.06 (InternVL2)Hurt
Co-Steer vs strongest baseline BAP in black-box transferCo-Steer · Black-box commercial modelsASR (%): +7.62 to +8.95 pp over BAPImproved
visual-only perturbation (VAJM) for transferVAJM · Black-box commercial modelsASR (%): 10.55-14.69 vs vanilla 8.86-10.83No 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