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 27 篇，第 1 / 1 页

1. ICLR 2024Adversarial Feature Map Pruning for Backdoor
2. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
3. ICLR 2024Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
4. ICLR 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
5. ICLR 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
6. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
7. ICLR 2024BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
8. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
9. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
10. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
11. ICLR 2024Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
12. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
13. ICLR 2024Influencer Backdoor Attack on Semantic Segmentation
14. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
15. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
16. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
17. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
18. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
19. ICLR 2024Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
20. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
21. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
22. ICLR 2024Safe and Robust Watermark Injection with a Single OoD Image
23. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
24. ICLR 2024Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
25. ICLR 2024Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
26. ICLR 2024Universal Backdoor Attacks
27. ICLR 2024VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

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。