Research map / Adversarial robustness and security / Black-box and transfer attacks
QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval
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 QAIR with a 200-query limit instead of decision-based attacks | Black-box image retrieval attacks · CUB-200 | ASR: 0.04 -> 0.69; 0 -> 0.69 | Helped |
| Use QAIR with a 200-query limit instead of decision-based attacks | Black-box image retrieval attacks · SOP | ASR: 0.420 -> 0.904 | Helped |
| Use QAIR with a 200-query limit instead of decision-based attacks | Black-box image retrieval attacks · In-Shop | ASR: 0.948 -> 0.916 | Mixed |
| Increase QAIR's maximum query limit from 200 to 1000 | QAIR · CUB-200, SOP, and In-Shop | ASR: 0.69 -> 0.73; 0.904 -> 0.920; 0.916 -> 0.924 | Helped |
| Use QAIR with a 200-query limit on Bing Visual Search | Black-box visual search attack · Bing Visual Search, 1000 ImageNet images | ASR: 98% | Helped |
Closest papers by meaning
- Blackbox Attacks via Surrogate Ensemble Search (NeurIPS 2022 · similarity 0.88)
- You See What I Want You To See: Exploring Targeted Black-Box Transferability Attack for Hash-Based Image Retrieval Systems (CVPR 2021 · similarity 0.87)
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK (ICLR 2024 · similarity 0.87)
- Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection (NeurIPS 2024 · similarity 0.86)
- Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior (ICML 2024 · similarity 0.86)
- Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models (NeurIPS 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.