Research map / Adversarial robustness and security / Backdoor and poisoning
Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
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.
Closest papers by meaning
- Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only (ICLR 2023 · similarity 0.91)
- A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives (AAAI 2024 · similarity 0.90)
- Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse (NeurIPS 2026 · similarity 0.89)
- A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers (NeurIPS 2025 · similarity 0.89)
- Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks (ICLR 2025 · similarity 0.89)
- Conditional Backdoor Attack via JPEG Compression (AAAI 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.