Research map / Adversarial robustness and security / Certified and empirical robustness
Characterizing the Evasion Attackability of Multi-label Classifiers
Zhuo Yang, Yufei Han, Xiangliang 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 GASE label expansion instead of random, oblivious, or loss-guided label search | Multi-label classifiers evaluated with PGD · Creepware, Genbase, VOC2012, Planet | average number of flipped labels | Improved |
| Use GASE instead of primitive greedy search (PGS) | Multi-label classifiers evaluated with PGD · Creepware, Genbase, VOC2012, Planet | average number of flipped labels | No clear effect |
| Add a low-rank nuclear-norm constraint (ablation) | Linear SVM and DNN multi-label classifiers · Creepware, Genbase, VOC2012, Planet | attackability indicator | Improved |
| Add adversarial training without a low-rank constraint (ablation) | Linear SVM and DNN multi-label classifiers · Creepware, Genbase, VOC2012, Planet | attackability indicator | No clear effect |
| Combine adversarial training with a low-rank nuclear-norm constraint (ablation) | Linear SVM and DNN multi-label classifiers · Creepware, Genbase, VOC2012, Planet | attackability indicator | Improved |
| Increase the strength of the nuclear-norm constraint (ablation) | Linear SVM and DNN multi-label classifiers · Unperturbed test data across four datasets | classification accuracy | Hurt |
Closest papers by meaning
- MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples (NeurIPS 2022 · similarity 0.89)
- Semantic-Aware Multi-Label Adversarial Attacks (CVPR 2024 · similarity 0.88)
- PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches (CVPR 2025 · similarity 0.86)
- Generalization Bound and New Algorithm for Clean-Label Backdoor Attack (ICML 2024 · similarity 0.85)
- Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement (CVPR 2024 · similarity 0.85)
- Adversarial Training for Defense Against Label Poisoning Attacks (ICLR 2025 · similarity 0.84)
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.
