Research map / Adversarial robustness and security / Black-box and transfer attacks
Towards Transferable Targeted Adversarial Examples
Read the paperCheck 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 |
|---|---|---|---|
| Add feature loss (dual discrimination) to label loss (ablation) | TTAA · Ablation on three source-target pairs | targeted fooling rate (%): improves significantly over label loss alone | Helped |
| Add random perturbation dropping (RPD) (ablation) | TTAA · Ablation on three source-target pairs | targeted fooling rate (%) | Helped |
| Use feature-label dual discrimination with TTAA vs TTP baseline in cross-domain | TTAA · Cross-domain, Dense-121 to Res-50 | targeted fooling rate (%): about 13.5% higher TFR than TTP | Helped |
| Adversarial training of target models (defense) | TTAA · Cross-domain against adversarially trained targets | targeted fooling rate (%): slight decrease vs non-robust case; still above TTP | Mixed |
Closest papers by meaning
- Delving into Transferable Adversarial Examples and Black-box Attacks (ICLR 2017 · similarity 0.95)
- Towards Transferable Targeted Attack (CVPR 2020 · similarity 0.95)
- A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks (NeurIPS 2021 · similarity 0.91)
- Boosting Adversarial Transferability through Augmentation in Hypothesis Space (CVPR 2025 · similarity 0.90)
- AIM: Additional Image Guided Generation of Transferable Adversarial Attacks (AAAI 2025 · similarity 0.89)
- Rethinking Model Ensemble in Transfer-based Adversarial Attacks (ICLR 2024 · similarity 0.88)
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.