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 5 / 14 页

  1. NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
  2. NeurIPS 2026Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
  3. NeurIPS 2026Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
  4. NeurIPS 2026Sequential Membership Inference Attacks
  5. NeurIPS 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
  6. NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
  7. NeurIPS 2026SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
  8. NeurIPS 2026Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
  9. NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
  10. NeurIPS 2026Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
  11. NeurIPS 2026The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
  12. NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
  13. NeurIPS 2026Towards Universal Black-box Attacks on Graph Neural Networks
  14. NeurIPS 2026TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
  15. NeurIPS 2026TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
  16. NeurIPS 2026Training-Based Backdoors Are Not Cryptographic
  17. NeurIPS 2026Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
  18. NeurIPS 2026When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
  19. NeurIPS 2026When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
  20. CVPR 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
  21. CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
  22. CVPR 2025Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
  23. CVPR 2025CDI: Copyrighted Data Identification in Diffusion Models
  24. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
  25. CVPR 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
  26. CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
  27. CVPR 2025Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
  28. CVPR 2025FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
  29. CVPR 2025From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
  30. CVPR 2025Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization
  31. CVPR 2025Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
  32. CVPR 2025Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation
  33. CVPR 2025Improving Transferable Targeted Attacks with Feature Tuning Mixup
  34. CVPR 2025Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
  35. CVPR 2025Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
  36. CVPR 2025Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
  37. CVPR 2025Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models
  38. ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
  39. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
  40. ICLR 2025ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification
  41. ICLR 2025Adversarial Attacks on Data Attribution
  42. ICLR 2025Adversarial Machine Unlearning
  43. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
  44. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
  45. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
  46. ICLR 2025Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
  47. ICLR 2025Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
  48. ICLR 2025BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
  49. ICLR 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
  50. ICLR 2025Can a Large Language Model be a Gaslighter?

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