AI Paper Atlas

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

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples

Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider, Tanzim Mahfuz, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 4 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
train attack-combination weights instead of using random weights (ablation)DASH · CIFAR-100, Cui2024ASR (no post-processing, %): 80.00 -> 100.00Improved
train attack-combination weights instead of using random weights (ablation)DASH · CIFAR-100, Cui2024SSIM (x100): 90.86 -> 94.43Improved
chain two stages instead of one (ablation)DASH · CIFAR-100, Cui2024average ASR (%): 51.88 -> 99.49Improved
chain three stages instead of two (ablation)DASH · CIFAR-100, Cui2024average ASR (%): 99.49 -> 99.77No clear effect
increase stages from 3 to 5 (ablation)DASH · CIFAR-100, Cui2024SSIM (x100): 94.43 -> 92.92Hurt
increase stages from 3 to 5 (ablation)DASH · CIFAR-100, Cui2024average ASR (%): 99.77 -> 99.98Improved
use only one stage versus more stages (ablation)DASH · CIFAR-100, Cui2024SSIM (x100): 98.48 (1 stage) vs 94.43 (3 stages)Mixed
compose multiple base attacks with learned weights versus the best single attackDASH vs CW · CIFAR-100, Cui2024average ASR (%): 84.14 -> 99.77Improved
use DASH instead of AdvAD on ImageNet robust modelSalman2020 ImageNet-1k · ImageNet-1k, Salman2020SSIM (x100): 71.30 -> 96.52Improved
transfer learned weights across models and datasets (ablation)DASH · cross-model weight transferaverage ASR (%)No clear effect
use DASH surrogate on Addepalli2022 instead of AdvAD for transferDASH · CIFAR-100 transfer, surrogate Addepalli2022average transfer ASR (%): 64.70 -> 63.30No clear effect
use DASH instead of DiffAttack for transfer from Cui2024DASH · CIFAR-100 transfer, surrogate Cui2024average transfer ASR (%): 74.74 -> 84.62Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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