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 87 篇，第 1 / 2 页

  1. ICLR 2026BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
  2. ICLR 2026Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
  3. ICLR 2026Black-Box Privacy Attacks on Shared Representations in Multitask Learning
  4. ICLR 2026Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
  5. ICLR 2026Defending against Backdoor Attacks via Module Switching
  6. ICLR 2026Detecting Temporal Misalignment Attacks in Multimodal Fusion for Autonomous Driving
  7. ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
  8. ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
  9. ICLR 2026Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
  10. ICLR 2026No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
  11. ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
  12. ICLR 2026Protection against Source Inference Attacks in Federated Learning
  13. ICLR 2026Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
  14. ICLR 2026Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
  15. ICLR 2026ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
  16. ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
  17. ICLR 2026STEDiff: Revealing the Spatial and Temporal Redundancy of Backdoor Attacks in Text-to-Image Diffusion Models
  18. ICLR 2026Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP
  19. ICLR 2026TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models
  20. ICLR 2026Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
  21. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
  22. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
  23. ICLR 2025Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
  24. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
  25. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
  26. ICLR 2025Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
  27. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
  28. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
  29. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
  30. ICLR 2025Detecting Backdoor Samples in Contrastive Language Image Pretraining
  31. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
  32. ICLR 2025Energy-based Backdoor Defense Against Federated Graph Learning
  33. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
  34. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
  35. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
  36. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
  37. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
  38. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
  39. ICLR 2025Protecting against simultaneous data poisoning attacks
  40. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
  41. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
  42. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
  43. ICLR 2025Robustness Inspired Graph Backdoor Defense
  44. ICLR 2025UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping
  45. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
  46. ICLR 2024Adversarial Feature Map Pruning for Backdoor
  47. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
  48. ICLR 2024Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
  49. ICLR 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
  50. ICLR 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

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