Research map / Adversarial robustness and security / Black-box and transfer attacks
Adversarial Attack on Deep Product Quantization Network for Image Retrieval
Yan Feng, Bin Chen, Tao Dai, Shu-Tao Xia
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 |
|---|---|---|---|
| Use PQ-AG rather than the basic deep-feature attack | AlexNet product-quantized retrieval · CIFAR-10, 16-bit, SDC | mAP: 27.5 -> 12.3 | Improved |
| Use PQ-AG rather than the basic deep-feature attack | AlexNet product-quantized retrieval · NUS-WIDE, 16-bit, SDC | mAP: 47.7 -> 28.9 | Improved |
| Attack the overall centroid distribution instead of only its peak (ablation) | PQ-AG · CIFAR-10, 16-bit AlexNet, SDC | mAP: 13.7 -> 12.3 | Improved |
| Attack the overall centroid distribution instead of only its peak (ablation) | PQ-AG · NUS-WIDE, 16-bit AlexNet, SDC | mAP: 31.5 -> 28.9 | Improved |
| Attack the overall centroid distribution instead of only its peak (ablation) | PQ-AG · CIFAR-10, 16-bit AlexNet, ADC | mAP: 10.3 -> 10.2 | Improved |
| Attack the overall centroid distribution instead of only its peak (ablation) | PQ-AG · NUS-WIDE, 16-bit AlexNet, ADC | mAP: 30.3 -> 28.2 | Improved |
| Use AOD against jointly trained rather than pretrained retrieval models | PQ-AG · CIFAR-10, 16-bit AlexNet, white-box | mAP | Mixed |
| Generate adversarial queries against one code length and use them against another | AOD · CIFAR-10, AlexNet, code lengths 16, 24, and 36 bits | mAP | Improved |
| Transfer adversarial queries between different CNN model families | AOD · CIFAR-10, ResNet and VGG models | mAP: 24.9% | Improved |
| Transfer adversarial queries among models within the same family | AOD · CIFAR-10, ResNet models | mAP: 68.5% | Improved |
| Transfer adversarial queries among models within the same family | AOD · CIFAR-10, VGG models | mAP: 51.6% | Improved |
Closest papers by meaning
- Adversarial Examples Generation for Deep Product Quantization Networks on Image Retrieval (TPAMI 2022 · similarity 0.95)
- Product Quantization Network for Fast Image Retrieval (ECCV 2018 · similarity 0.86)
- Improving Query Efficiency of Black-box Adversarial Attack (ECCV 2020 · similarity 0.86)
- Deep Supervised Adversarial Robust Hashing for Retrieval (TPAMI 2026 · similarity 0.86)
- QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval (CVPR 2021 · similarity 0.86)
- VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models (AAAI 2024 · 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.
