Research map / Adversarial robustness and security / Backdoor and poisoning
CL-Guard: Defending DNNs Against Backdoors via Fine-Grained Neuron Analysis and Collaborative Dual-Network Learning
Jie Xiao, Yuhao Huang, Yanjiao Gao, Aizhu Liu, Zhezhao Yang, Xinyue Yu, Qianwei Zhou, Fan Terry 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 CL-Guard instead of FT-SAM | PreActResNet18 · Tiny-ImageNet avg SEI | SEI: 58.30 -> 92.94 | Improved |
| use CL-Guard instead of FT-SAM | PreActResNet18 · Average over settings | SEI: +21.23% | Improved |
| use CL-Guard instead of best baseline | VGG-16 · GTSRB | ASR/ACC/SEI: <12.26, 0.01, 11.07> pp | Improved |
| use critical neuron selection instead of random neurons (Sc-1) (ablation) | CL-Guard · CIFAR-10 attacks | ASR/ACC/SEI | Improved |
| add dual-network collaborative training instead of plain fine-tuning (Sc-2) (ablation) | CL-Guard · CIFAR-10 attacks | ASR/ACC/SEI | Improved |
| reduce mask coverage m_c (ablation) | CL-Guard · CIFAR-10 / Tiny-ImageNet | ACC/SEI | Mixed |
| vary poisoning rate 1% to 50% (ablation) | CL-Guard · CIFAR-10, GTSRB | SEI: +19.52% to -1.89% over best baseline | Mixed |
Closest papers by meaning
- Defending against Backdoor Attacks via Module Switching (ICLR 2026 · similarity 0.89)
- Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation (AAAI 2025 · similarity 0.89)
- Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness (NeurIPS 2024 · similarity 0.88)
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model (NeurIPS 2025 · similarity 0.87)
- BAN: Detecting Backdoors Activated by Adversarial Neuron Noise (NeurIPS 2024 · similarity 0.87)
- REFINE: Inversion-Free Backdoor Defense via Model Reprogramming (ICLR 2025 · similarity 0.86)
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.
