AI Paper Atlas

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

PGA: Prior-free Generative Attack for Practical No-box Scenario

Hongyu Peng, Xiang Yuan, Gong Cheng

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition

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 Curriculum-Guided Micro-Robust Optimization to surrogate training (ablation)BIA generator · ImageNet cross-model (CNNs)AVGc ASR (%): 54.18 -> 65.44Improved
add Region-Aware Consistent Perturbation Learning to generator training (ablation)BIA generator · ImageNet cross-model (CNNs)AVGc ASR (%): 54.18 -> 62.11Improved
combine CMRO and RCPL (ablation)PGA · ImageNet cross-model (ViTs/MLPs)AVGv ASR (%): 32.95 -> 47.50Improved
increase number of regions K from 1 to 4 (ablation)RCPL · ImageNet cross-model (CNNs)AVGc ASR (%): 65.44 -> 71.39Improved
increase number of regions K from 4 to 9 (ablation)RCPL · ImageNet cross-model (ViTs/MLPs)AVGv ASR (%): 47.50 -> 42.29Hurt
delay micro-robust training until epoch 200 with tau_max 0.01 instead of other strength or timing (ablation)CMRO · ImageNet cross-modelAVGc and AVGv ASRMixed
use generative attacks with SimSiam surrogate instead of iterative PNS attacksPNS attacks · ImageNet cross-modelASR: AGS AVGc 50.26 vs BIA 54.18Improved
add DA or RN variants to BIABIA · ImageNet cross-model (CNNs)AVGc ASR (%): 54.18 -> 54.32 (DA), 54.51 (RN)No clear effect
use PGA instead of strongest baseline at eps=10generative attack · ImageNet cross-model (eps=10)AVGc ASR (%): 34.22 -> 50.11 (BIA vs PGA)Improved
use PGA instead of baselines against defensesgenerative attack · ImageNet under defensesAVGd ASR (%): 56.88 -> 72.16 (FACL vs PGA)Improved
reduce perturbation budget from 16 to 15 without retraining (ablation)PGA · ImageNet image qualityAVGc ASR (%): 71.39 -> 68.95Hurt
use PGA instead of baselines for cross-task attackFaster R-CNN · MS COCO detection (ImageNet-trained generator)AP (%): 21.35 -> 17.60 (GAPF vs PGA)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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