AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

GAMA: Generative Adversarial Multi-Object Scene Attacks

Abhishek Aich, Calvin-Khang Ta, Akash A Gupta, Chengyu Song, Srikanth Krishnamurthy, M. Salman Asif, Amit Roy-Chowdhury

NeurIPS 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 9 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
GAMA versus best baseline (CLIP-guided losses)GAMA generative attack · VOC->VOC, Res152 surrogateavg score, lower=better attack: 52.81 -> 37.49Improved
GAMA versus best baselineGAMA generative attack · VOC->ImageNet, VGG19 surrogateavg score, lower=better attack: 35.75 -> 19.61Improved
GAMA versus best baselineGAMA generative attack · COCO->COCO, VGG19 surrogateavg score, lower=better attack: 17.68 -> 18.54Mixed
GAMA versus best baselineGAMA generative attack · COCO->ImageNet, VGG19 surrogateavg score, lower=better attack: 17.10 -> 19.83Mixed
GAMA versus best baselineGAMA generative attack · COCO->ImageNet, Den169 surrogateavg score, lower=better attack: 29.52 -> 12.04Improved
GAMA versus best baseline under NRP purifierGAMA generative attack · COCO->ImageNet, Den169 surrogateavg score, lower=better attack: 23.68 -> 11.41Improved
GAMA versus best baseline under median blurGAMA generative attack · COCO->ImageNet, Den169 surrogateavg score, lower=better attack: 37.95 -> 35.85Improved
use vision-transformer CLIP ViT-B/16 instead of RN50 (ablation)GAMA generative attack · VOC->VOC, Res152 surrogatehamming score on Res152 victim: 67.24 -> 45.57Mixed
add each loss (surrogate, image-embedding, text-embedding) in turn (ablation)GAMA generative attack · VOC, Res152 surrogateattack strengthImproved

Later papers that compared with this method

3 later accepted papers report GAMA as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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