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 24 篇，第 1 / 1 页

1. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
2. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
3. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
4. ICML 2024Causality Based Front-door Defense Against Backdoor Attack on Language Models
5. ICML 2024Data Poisoning Attacks against Conformal Prediction
6. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
7. ICML 2024Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
8. ICML 2024Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
9. ICML 2024Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
10. ICML 2024Fast Adversarial Attacks on Language Models In One GPU Minute
11. ICML 2024FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
12. ICML 2024Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
13. ICML 2024IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
14. ICML 2024Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
15. ICML 2024Low-Cost High-Power Membership Inference Attacks
16. ICML 2024Membership Inference Attacks on Diffusion Models via Quantile Regression
17. ICML 2024Privacy Attacks in Decentralized Learning
18. ICML 2024Revisiting Character-level Adversarial Attacks for Language Models
19. ICML 2024SHINE: Shielding Backdoors in Deep Reinforcement Learning
20. ICML 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
21. ICML 2024TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
22. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
23. ICML 2024The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline
24. ICML 2024Toward Availability Attacks in 3D Point Clouds

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。