Research map / Adversarial robustness and security / Attacks on text and graphs
Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes
Mingjun Yin, Shasha Li, Zikui Cai, Chengyu Song, M. Salman Asif, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy
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 |
|---|---|---|---|
| check coarse-grained location as well as category in the consistency score (SCENE-BERT Strict vs Relax) (ablation) | SCENE-BERT · PASCAL VOC (F-RCNN) | ROC-AUC | Improved |
| use context-aware SCENE-BERT instead of context-agnostic Feature Squeeze, misclassification attacks | Faster R-CNN detector · PASCAL VOC | ROC-AUC: 0.53 -> 0.88 | Improved |
| use SCENE-BERT instead of Feature Squeeze, hiding attacks on COCO | Faster R-CNN detector · MS COCO | ROC-AUC: 0.74 -> 0.55 | Hurt |
| use SCENE-BERT instead of Feature Squeeze, hiding attacks | YOLO detector · PASCAL VOC | ROC-AUC: 0.75 -> 0.74 | No clear effect |
| use SCENE-BERT instead of Feature Squeeze, appearing attacks | YOLO detector · MS COCO | ROC-AUC: 0.67 -> 0.88 | Improved |
| use region-level SCEME (Faster R-CNN specific) instead of model-agnostic SCENE-BERT, hiding attacks | Faster R-CNN detector · PASCAL VOC | ROC-AUC: 0.74 -> 0.95 | Improved |
| use SCENE-BERT instead of SCEME for appearing attacks | Faster R-CNN detector · PASCAL VOC | ROC-AUC: 0.87 -> 0.88 | No clear effect |
Closest papers by meaning
- Visual Adversarial Examples Jailbreak Aligned Large Language Models (AAAI 2024 · similarity 0.87)
- Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks (CVPR 2025 · similarity 0.86)
- Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models (CVPR 2025 · similarity 0.86)
- GLOW: Global Layout Aware Attacks on Object Detection (CVPR 2024 · similarity 0.85)
- Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models (NeurIPS 2024 · similarity 0.85)
- SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments (CVPR 2025 · similarity 0.85)
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.
