Research map / Adversarial robustness and security / Attacks on text and graphs
Dynamic Generative Targeted Attacks With Pattern Injection
Weiwei Feng, Nanqing Xu, Tianzhu Zhang, Yongdong Zhang
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 dynamic generative targeted attacks instead of TTP | Targeted attacks using Res152 as substitute · ImageNet-NeurIPS validation set; normally trained models | average attack success rate (%): 5.28% | Improved |
| Use dynamic generative targeted attacks instead of TTP | Targeted attacks using Res152 as substitute · ImageNet-NeurIPS validation set; robust models | average attack success rate (%): 4.45% | Improved |
| Increase target samples used for training (ablation) | Proposed dynamic generative attack model · ImageNet-NeurIPS validation set; victim models Vgg-16, GoogleNet, and Inc-v3 | attack success rate (%) | Improved |
| Increase learnable convolution kernels, with performance leveling off beyond 4 (ablation) | Proposed dynamic generative attack model · ImageNet-NeurIPS validation set; victim models Vgg-16, GoogleNet, and Inc-v3 | attack success rate (%) | Mixed |
Closest papers by meaning
- On Generating Transferable Targeted Perturbations (ICCV 2021 · similarity 0.88)
- Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection (ECCV 2024 · similarity 0.88)
- Towards Transferable Targeted Adversarial Examples (CVPR 2023 · similarity 0.87)
- Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks (ECCV 2022 · similarity 0.87)
- AIM: Additional Image Guided Generation of Transferable Adversarial Attacks (AAAI 2025 · similarity 0.87)
- Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models (CVPR 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.
