AI Paper Atlas

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

Scaling Laws for Black-box Adversarial Attacks

Chuan Liu, Huanran Chen, Yichi Zhang, Jun Zhu, Yinpeng Dong

ECCV 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 11 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
scale the number of surrogate models in the ensemble (log2 T from 0 to 6) with SSA-CWA (ablation)SSA-CWA ensemble attack · Targeted attack on standard classifiers (ImageNet NIPS17)ASR: ASR increases linearly with log T; each doubling of T gives a consistent gainImproved
scale surrogate ensemble size against defended models (ablation)SSA-CWA ensemble attack · Defended models (DiffPure, adversarially trained, HGD)ASR: DiffPure over 30%, adversarially trained models over 20%, HGD over 50%Improved
scale surrogate ensemble size, evaluated on MLLMs (ablation)SSA-CWA ensemble attack · MLLM targets (LLaVA-1.5-7B, Qwen-2.5-VL-7B, Llama-3.2-11B-Vision)ASRImproved
scale CLIP surrogate ensemble from 1 to 12 models (ablation)SSA-CWA on CLIP ensemble · 7 SOTA MLLMs (eps 16/255)ASR: 85.0% on GPT-4o and 90.0% on Qwen3-VL-235B at T=12Improved
scale ensemble in the untargeted setting (ablation)SSA-CWA ensemble attack · Untargeted attack (Swin-B, ConvNeXt-B, ResNeXt50, eps 2/255)ASRImproved
use logit-averaging ensembles (MI-FGSM, DI-MI-FGSM, VMI-FGSM) instead of gradient-aligning optimizers (ablation)ensemble attack · Targeted sea lion, standard classifiersASRHurt
use advanced ensemble optimizers (MI-CWA, VMI-CWA, MI-SVRE) that resolve gradient conflict (ablation)ensemble attack · Targeted sea lion, standard classifiersASRImproved
add DI or VMI components to logit-ensemble MI-FGSM (ablation)logit-averaging ensemble · Targeted sea lion, standard classifiersASRNo clear effect
increase ensemble size T for naive MI-FGSM logit ensemble (ablation)naive logit ensemble · gradient norm analysisgradient normHurt

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