后门攻击论文趋势 2023–2026

主要结论

• 后门攻击论文从 2023 年的 73 篇增长到 2026 年的 111 篇，三年间扩大到约 1.5 倍。
• NeurIPS 是发后门攻击论文最多的会议，2023–2026 年共 124 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 16 篇。
• 在「安全与可信」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的水印是 9.3 倍，后门攻击是 1.5 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
• ICML 2026Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning
• ICLR 2026Defending against Backdoor Attacks via Module Switching
• CVPR 2026Eliminate Distance Differences Induced by Backdoor Attacks Layer-Selective Training and
• NeurIPS 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
• ICML 2025A Closer Look at Backdoor Attacks on CLIP
• ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
• CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
• NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
• ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
• ICLR 2024Adversarial Feature Map Pruning for Backdoor
• CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
• NeurIPS 2023A Unified Detection Framework for Inference-Stage Backdoor Defenses
• ICML 2023Data Poisoning Attacks Against Multimodal Encoders
• ICLR 2023Adversarial Attacks on Adversarial Bandits
• CVPR 2023Architectural Backdoors in Neural Networks
• NeurIPS 2026AI Models Can Provably Hide Arbitrary Capabilities
• ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
• ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
• CVPR 2026Logit-Margin Repulsion for Backdoor Defense

全部后门攻击论文

共 21 篇，第 1 / 1 页

1. NeurIPS 2023A Unified Detection Framework for Inference-Stage Backdoor Defenses
2. NeurIPS 2023A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
3. NeurIPS 2023BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
4. NeurIPS 2023Blurred-Dilated Method for Adversarial Attacks
5. NeurIPS 2023Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
6. NeurIPS 2023Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
7. NeurIPS 2023Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense
8. NeurIPS 2023FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
9. NeurIPS 2023Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
10. NeurIPS 2023IBA: Towards Irreversible Backdoor Attacks in Federated Learning
11. NeurIPS 2023Label Poisoning is All You Need
12. NeurIPS 2023ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
13. NeurIPS 2023QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks
14. NeurIPS 2023RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks
15. NeurIPS 2023Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks
16. NeurIPS 2023Scalable Membership Inference Attacks via Quantile Regression
17. NeurIPS 2023Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
18. NeurIPS 2023Static and Sequential Malicious Attacks in the Context of Selective Forgetting
19. NeurIPS 2023Towards Stable Backdoor Purification through Feature Shift Tuning
20. NeurIPS 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
21. NeurIPS 2023What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

常见问题

2023–2026 年四大会议一共有多少篇后门攻击论文？

共 381 篇，按年份分别是 2023 年 73 篇、2024 年 105 篇、2025 年 92 篇、2026 年 111 篇。

NeurIPS 2026 有多少篇后门攻击论文？

NeurIPS 2026 有 36 篇后门攻击论文，上一届是 31 篇。

ICLR 2026 有多少篇后门攻击论文？

ICLR 2026 有 20 篇后门攻击论文，上一届是 25 篇。

ICML 2026 有多少篇后门攻击论文？

ICML 2026 有 36 篇后门攻击论文，上一届是 17 篇。

CVPR 2026 有多少篇后门攻击论文？

CVPR 2026 有 19 篇后门攻击论文，上一届是 19 篇。

哪个会议的后门攻击论文最多？

NeurIPS，2023–2026 年共 124 篇。