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 18 篇，第 1 / 1 页

1. CVPR 2026AdapAction Adaptive Target Action Backdoor Attack against GUI Agents
2. CVPR 2026AntiStyler Defending Object Detection Models Against Adversarial Patch Attacks Using
3. CVPR 2026BlackMirror Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
4. CVPR 2026Eliminate Distance Differences Induced by Backdoor Attacks Layer-Selective Training and
5. CVPR 2026Exposing Functional Fusion A New Class of Strategic Backdoor in
6. CVPR 2026FORCE Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
7. CVPR 2026Fractal Camouflage A Bio-Inspired Approach for Multi-Scale Adversarial Attacks in
8. CVPR 2026Good Can Sometimes be Bad A Unified Attack against 3D
9. CVPR 2026IAG Input-aware Backdoor Attack on VLM-based Visual Grounding
10. CVPR 2026Logit-Margin Repulsion for Backdoor Defense
11. CVPR 2026Out of Sight Out of Track Adversarial Attacks on Propagation-based
12. CVPR 2026Phantom Physical Object Interactions as Dynamic Triggers for NMS-Exploited Backdoors
13. CVPR 2026RaPA Enhancing Transferable Targeted Attacks via Random Parameter Pruning
14. CVPR 2026Towards Human-Imperceptible Backdoor Attacks on Text-to-Image Diffusion Models
15. CVPR 2026Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
16. CVPR 2026Towards Stealthy and Effective Backdoor Attacks on Lane Detection A
17. CVPR 2026VCP-Attack Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large
18. CVPR 2026When Robots Obey the Patch Universal Transferable Patch Attacks on

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。