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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| GAMA versus best baseline (CLIP-guided losses) | GAMA generative attack · VOC->VOC, Res152 surrogate | avg score, lower=better attack: 52.81 -> 37.49 | Improved |
| GAMA versus best baseline | GAMA generative attack · VOC->ImageNet, VGG19 surrogate | avg score, lower=better attack: 35.75 -> 19.61 | Improved |
| GAMA versus best baseline | GAMA generative attack · COCO->COCO, VGG19 surrogate | avg score, lower=better attack: 17.68 -> 18.54 | Mixed |
| GAMA versus best baseline | GAMA generative attack · COCO->ImageNet, VGG19 surrogate | avg score, lower=better attack: 17.10 -> 19.83 | Mixed |
| GAMA versus best baseline | GAMA generative attack · COCO->ImageNet, Den169 surrogate | avg score, lower=better attack: 29.52 -> 12.04 | Improved |
| GAMA versus best baseline under NRP purifier | GAMA generative attack · COCO->ImageNet, Den169 surrogate | avg score, lower=better attack: 23.68 -> 11.41 | Improved |
| GAMA versus best baseline under median blur | GAMA generative attack · COCO->ImageNet, Den169 surrogate | avg score, lower=better attack: 37.95 -> 35.85 | Improved |
| use vision-transformer CLIP ViT-B/16 instead of RN50 (ablation) | GAMA generative attack · VOC->VOC, Res152 surrogate | hamming score on Res152 victim: 67.24 -> 45.57 | Mixed |
| add each loss (surrogate, image-embedding, text-embedding) in turn (ablation) | GAMA generative attack · VOC, Res152 surrogate | attack strength | Improved |
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.
- Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks (ECCV 2024 · better on 5 of 6 shared results)
- Towards Understanding and Improving Adversarial Robustness of Vision Transformers (CVPR 2024 · better on 3 of 3 shared results)
- Mutual-Modality Adversarial Attack with Semantic Perturbation (AAAI 2024 · better on 1 of 1 shared result)
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
- Attention! Your Vision Language Model Could Be Maliciously Manipulated (NeurIPS 2025 · similarity 0.88)
- Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models (CVPR 2025 · similarity 0.87)
- Image Hijacks: Adversarial Images can Control Generative Models at Runtime (ICML 2024 · similarity 0.87)
- Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks (CVPR 2025 · similarity 0.87)
- Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models (CVPR 2025 · similarity 0.86)
- SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments (CVPR 2025 · similarity 0.86)
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.
