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 9 / 14 页

  1. CVPR 2024LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
  2. CVPR 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
  3. CVPR 2024OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition
  4. CVPR 2024Overload: Latency Attacks on Object Detection for Edge Devices
  5. CVPR 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
  6. CVPR 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
  7. CVPR 2024Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
  8. CVPR 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
  9. CVPR 2024Privacy-Preserving Optics for Enhancing Protection in Face De-Identification
  10. CVPR 2024Re-thinking Data Availability Attacks Against Deep Neural Networks
  11. CVPR 2024Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
  12. CVPR 2024Semantic-Aware Multi-Label Adversarial Attacks
  13. CVPR 2024SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models
  14. CVPR 2024Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
  15. CVPR 2024Ungeneralizable Examples
  16. CVPR 2024Validating Privacy-Preserving Face Recognition under a Minimum Assumption
  17. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
  18. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
  19. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
  20. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
  21. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
  22. ICLR 2024Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
  23. ICLR 2024Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
  24. ICLR 2024Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
  25. ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
  26. ICLR 2024Deceptive Fairness Attacks on Graphs via Meta Learning
  27. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
  28. ICLR 2024Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
  29. ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
  30. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
  31. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
  32. ICLR 2024Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
  33. ICLR 2024FedInverse: Evaluating Privacy Leakage in Federated Learning
  34. ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
  35. ICLR 2024Fixed-Budget Differentially Private Best Arm Identification
  36. ICLR 2024GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
  37. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
  38. ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
  39. ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
  40. ICLR 2024IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
  41. ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
  42. ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
  43. ICLR 2024Language Model Detectors Are Easily Optimized Against
  44. ICLR 2024Language Model Inversion
  45. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
  46. ICLR 2024Leave-one-out Distinguishability in Machine Learning
  47. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
  48. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
  49. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
  50. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning

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