Research map / Adversarial robustness and security / Black-box and transfer attacks
Zero-Query Transfer Attacks on Context-Aware Object Detectors
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use co-occurrence context to make simultaneous, context-consistent changes to scene objects rather than choosing attack labels without context | Zero-query attack · VOC07 test, ε=50, WB (Faster R-CNN) | fooling rate: 34.0 -> 90.0 | Helped |
| Add PSPM-guided selection of context-consistent attack plans (ablation) | ZQA · VOC07 test, ε=50, BB1 (RetinaNet) | fooling rate: 46.6 -> 51.2 | Helped |
| Add PSPM-guided selection of context-consistent attack plans (ablation) | ZQA · VOC07 test, ε=50, WB (Faster R-CNN) | fooling rate: 90.0 -> 92.6 | Helped |
| Allow repeated victim-model feedback and up to 5 query rounds instead of one zero-query attempt | Few-Query attack · VOC07 test, ε=50, BB1 (RetinaNet) | fooling rate: 51.2 -> 61.8 | Helped |
| Reduce the perturbation budget from ε=50 to ε=10 | ZQA-PSPM · VOC07 test, WB (Faster R-CNN) | fooling rate: 92.6 -> 70.6 | Hurt |
Closest papers by meaning
- Transferable Adversarial Attacks for Object Detection Using Object-Aware Significant Feature Distortion (AAAI 2024 · similarity 0.87)
- GLOW: Global Layout Aware Attacks on Object Detection (CVPR 2024 · similarity 0.87)
- Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature (AAAI 2025 · similarity 0.86)
- Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis (CVPR 2025 · similarity 0.86)
- Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks (CVPR 2025 · similarity 0.86)
- Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection (NeurIPS 2024 · 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.