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 124 篇，第 2 / 3 页

  1. NeurIPS 2025Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?
  2. NeurIPS 2025Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
  3. NeurIPS 2025LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks
  4. NeurIPS 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learning
  5. NeurIPS 2025Provable Watermarking for Data Poisoning Attacks
  6. NeurIPS 2025RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
  7. NeurIPS 2025SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
  8. NeurIPS 2025SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
  9. NeurIPS 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
  10. NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
  11. NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
  12. NeurIPS 2025The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses
  13. NeurIPS 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
  14. NeurIPS 2025Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
  15. NeurIPS 2025TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks
  16. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
  17. NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
  18. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
  19. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
  20. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
  21. NeurIPS 2024BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
  22. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
  23. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
  24. NeurIPS 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
  25. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
  26. NeurIPS 2024Data Free Backdoor Attacks
  27. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
  28. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
  29. NeurIPS 2024Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
  30. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
  31. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
  32. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
  33. NeurIPS 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
  34. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
  35. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
  36. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
  37. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
  38. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
  39. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
  40. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
  41. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
  42. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
  43. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
  44. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
  45. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
  46. NeurIPS 2024Stealth edits to large language models
  47. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
  48. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
  49. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
  50. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits

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