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 10 / 14 页

  1. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
  2. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
  3. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
  4. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
  5. ICLR 2024RAIN: Your Language Models Can Align Themselves without Finetuning
  6. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
  7. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
  8. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
  9. ICLR 2024Sharpness-Aware Data Poisoning Attack
  10. ICLR 2024Tangent Transformers for Composition,Privacy and Removal
  11. ICLR 2024Teach LLMs to Phish: Stealing Private Information from Language Models
  12. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
  13. ICLR 2024The False Promise of Imitating Proprietary Language Models
  14. ICLR 2024The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
  15. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
  16. ICLR 2024Towards Poisoning Fair Representations
  17. ICLR 2024Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
  18. ICLR 2024Universal Backdoor Attacks
  19. ICLR 2024You Only Query Once: An Efficient Label-Only Membership Inference Attack
  20. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
  21. ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
  22. ICML 2024AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
  23. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
  24. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
  25. ICML 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
  26. ICML 2024Collective Certified Robustness against Graph Injection Attacks
  27. ICML 2024Data Poisoning Attacks against Conformal Prediction
  28. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
  29. ICML 2024Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
  30. ICML 2024Fast Adversarial Attacks on Language Models In One GPU Minute
  31. ICML 2024FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
  32. ICML 2024Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy
  33. ICML 2024Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
  34. ICML 2024Low-Cost High-Power Membership Inference Attacks
  35. ICML 2024Mean Estimation in the Add-Remove Model of Differential Privacy
  36. ICML 2024Membership Inference Attacks on Diffusion Models via Quantile Regression
  37. ICML 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
  38. ICML 2024Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
  39. ICML 2024Privacy Attacks in Decentralized Learning
  40. ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
  41. ICML 2024Privacy Profiles for Private Selection
  42. ICML 2024Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent
  43. ICML 2024Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
  44. ICML 2024Private Truly-Everlasting Robust-Prediction
  45. ICML 2024Provable Privacy with Non-Private Pre-Processing
  46. ICML 2024Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
  47. ICML 2024Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas
  48. ICML 2024Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD
  49. ICML 2024Revisiting Character-level Adversarial Attacks for Language Models
  50. ICML 2024Shifted Interpolation for Differential 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