隐私攻击论文趋势 2023–2026

成员推断等

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 698 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

隐私攻击论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202346242925124
202463534222180
202545832918175
2026551023824219

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

全部隐私攻击论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 698 篇，第 12 / 14 页

  1. NeurIPS 2024PrivCirNet: Efficient Private Inference via Block Circulant Transformation
  2. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
  3. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
  4. NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
  5. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
  6. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
  7. NeurIPS 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
  8. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
  9. NeurIPS 2024Scalable DP-SGD: Shuffling vs. Poisson Subsampling
  10. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
  11. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
  12. NeurIPS 2024SPEAR: Exact Gradient Inversion of Batches in Federated Learning
  13. NeurIPS 2024Stealth edits to large language models
  14. NeurIPS 2024SuperDeepFool: a new fast and accurate minimal adversarial attack
  15. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
  16. NeurIPS 2024The Limits of Differential Privacy in Online Learning
  17. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
  18. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
  19. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
  20. NeurIPS 2024United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
  21. NeurIPS 2024Watermarking Makes Language Models Radioactive
  22. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
  23. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
  24. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
  25. CVPR 2023Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
  26. CVPR 2023CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search
  27. CVPR 2023DartBlur: Privacy Preservation With Detection Artifact Suppression
  28. CVPR 2023Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning
  29. CVPR 2023Dynamic Generative Targeted Attacks With Pattern Injection
  30. CVPR 2023Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks
  31. CVPR 2023Enhancing the Self-Universality for Transferable Targeted Attacks
  32. CVPR 2023Ensemble-Based Blackbox Attacks on Dense Prediction
  33. CVPR 2023Learning To Generate Image Embeddings With User-Level Differential Privacy
  34. CVPR 2023Make Landscape Flatter in Differentially Private Federated Learning
  35. CVPR 2023Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks
  36. CVPR 2023Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization
  37. CVPR 2023Physical-World Optical Adversarial Attacks on 3D Face Recognition
  38. CVPR 2023Privacy-Preserving Adversarial Facial Features
  39. CVPR 2023Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses
  40. CVPR 2023Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks
  41. CVPR 2023Re-Thinking Model Inversion Attacks Against Deep Neural Networks
  42. CVPR 2023Reinforcement Learning-Based Black-Box Model Inversion Attacks
  43. CVPR 2023Robust Single Image Reflection Removal Against Adversarial Attacks
  44. CVPR 2023SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization
  45. CVPR 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition
  46. CVPR 2023The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks
  47. CVPR 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
  48. CVPR 2023Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
  49. CVPR 2023TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets
  50. ICLR 2023A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy

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 查隐私攻击在 ICLR 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": "privacy-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隐私攻击论文？
共 698 篇，按年份分别是 2023 年 124 篇、2024 年 180 篇、2025 年 175 篇、2026 年 219 篇。
NeurIPS 2026 有多少篇隐私攻击论文？
NeurIPS 2026 有 55 篇隐私攻击论文，上一届是 45 篇。
ICLR 2026 有多少篇隐私攻击论文？
ICLR 2026 有 102 篇隐私攻击论文，上一届是 83 篇。
ICML 2026 有多少篇隐私攻击论文？
ICML 2026 有 38 篇隐私攻击论文，上一届是 29 篇。
CVPR 2026 有多少篇隐私攻击论文？
CVPR 2026 有 24 篇隐私攻击论文，上一届是 18 篇。
哪个会议的隐私攻击论文最多？
ICLR，2023–2026 年共 262 篇。

「联邦与隐私」下的其他主题