后门攻击论文趋势 2023–2026

触发器与检测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 381 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

后门攻击论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232115112673
202436272418105
20253125171992
202636203619111

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

全部后门攻击论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 380 篇，第 5 / 8 页

  1. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
  2. NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
  3. CVPR 2024Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
  4. CVPR 2024Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models
  5. CVPR 2024Backdoor Defense via Test-Time Detecting and Repairing
  6. CVPR 2024BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
  7. CVPR 2024BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
  8. CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
  9. CVPR 2024GLOW: Global Layout Aware Attacks on Object Detection
  10. CVPR 2024Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
  11. CVPR 2024LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
  12. CVPR 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
  13. CVPR 2024Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers
  14. CVPR 2024One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning
  15. CVPR 2024Overload: Latency Attacks on Object Detection for Edge Devices
  16. CVPR 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
  17. CVPR 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
  18. CVPR 2024Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
  19. CVPR 2024Re-thinking Data Availability Attacks Against Deep Neural Networks
  20. CVPR 2024Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
  21. ICLR 2024Adversarial Feature Map Pruning for Backdoor
  22. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
  23. ICLR 2024Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
  24. ICLR 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
  25. ICLR 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  26. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
  27. ICLR 2024BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
  28. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
  29. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
  30. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
  31. ICLR 2024Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
  32. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
  33. ICLR 2024Influencer Backdoor Attack on Semantic Segmentation
  34. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
  35. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
  36. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
  37. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
  38. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
  39. ICLR 2024Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
  40. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
  41. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
  42. ICLR 2024Safe and Robust Watermark Injection with a Single OoD Image
  43. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
  44. ICLR 2024Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
  45. ICLR 2024Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
  46. ICLR 2024Universal Backdoor Attacks
  47. ICLR 2024VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
  48. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
  49. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
  50. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查后门攻击在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "backdoor-attacks"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「安全与可信」下的其他主题