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 262 篇，第 5 / 6 页

  1. ICLR 2024Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
  2. ICLR 2024FedInverse: Evaluating Privacy Leakage in Federated Learning
  3. ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
  4. ICLR 2024Fixed-Budget Differentially Private Best Arm Identification
  5. ICLR 2024GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
  6. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
  7. ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
  8. ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
  9. ICLR 2024IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
  10. ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
  11. ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
  12. ICLR 2024Language Model Detectors Are Easily Optimized Against
  13. ICLR 2024Language Model Inversion
  14. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
  15. ICLR 2024Leave-one-out Distinguishability in Machine Learning
  16. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
  17. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
  18. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
  19. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
  20. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
  21. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
  22. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
  23. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
  24. ICLR 2024RAIN: Your Language Models Can Align Themselves without Finetuning
  25. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
  26. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
  27. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
  28. ICLR 2024Sharpness-Aware Data Poisoning Attack
  29. ICLR 2024Tangent Transformers for Composition,Privacy and Removal
  30. ICLR 2024Teach LLMs to Phish: Stealing Private Information from Language Models
  31. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
  32. ICLR 2024The False Promise of Imitating Proprietary Language Models
  33. ICLR 2024The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
  34. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
  35. ICLR 2024Towards Poisoning Fair Representations
  36. ICLR 2024Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
  37. ICLR 2024Universal Backdoor Attacks
  38. ICLR 2024You Only Query Once: An Efficient Label-Only Membership Inference Attack
  39. ICLR 2023A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
  40. ICLR 2023Adversarial Attacks on Adversarial Bandits
  41. ICLR 2023Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
  42. ICLR 2023CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
  43. ICLR 2023Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
  44. ICLR 2023Differentially Private $L_2$-Heavy Hitters in the Sliding Window Model
  45. ICLR 2023Disparate Impact in Differential Privacy from Gradient Misalignment
  46. ICLR 2023Distributed Differential Privacy in Multi-Armed Bandits
  47. ICLR 2023Easy Differentially Private Linear Regression
  48. ICLR 2023Effective passive membership inference attacks in federated learning against overparameterized models
  49. ICLR 2023Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
  50. ICLR 2023Extracting Robust Models with Uncertain Examples

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