AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models

Yuanbo Li, Tianyang Xu, Cong Hu, Tao Zhou, Xiao-Jun Wu, Josef Kittler

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 2 citations (OpenAlex)

Read the paper

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
Use multi-paradigm collaborative optimization (MPCAttack) instead of the best single-paradigm attackMPCAttack · ImageNet, targeted, open-source MLLMsASR (%): 48.60 -> 63.33Improved
Use MPCAttack instead of FOA-Attack on closed-source modelsMPCAttack · ImageNet, untargeted, closed-source MLLMsASR (%): 82.63 -> 90.55Improved
Use MPCAttack instead of FOA-Attack on Flickr30KMPCAttack · Flickr30K, targeted, open-source MLLMsASR (%): 15.41 -> 29.54Improved
MPCAttack on Qwen2.5-VL-7B untargeted Flickr30K versus X-TransferMPCAttack · Flickr30K, untargeted, Qwen2.5-VL-7BASR (%): 42.84 -> 32.14Hurt
Add the cross-modal alignment paradigm (CLIP) (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Improved
Add the visual self-supervised paradigm (DINOv2) (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Improved
Add the multimodal understanding paradigm (InternVL3) (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Improved
Add the MPCO contrastive matching strategy (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Improved
Replace CLIP with SigLIP2 as cross-modal surrogate (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Hurt
Replace InternVL3-1B with InternVL3-2B (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Improved
Replace DINOv2 with DINOv3 (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)No clear effect
Use image-only features (lambda = 1) instead of intermediate image-text fusion weight (ablation)MPCAttack · ImageNet, open-source MLLMsASR (%)Hurt

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