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 209 篇，第 2 / 5 页

  1. NeurIPS 2026TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
  2. NeurIPS 2026Training-Based Backdoors Are Not Cryptographic
  3. NeurIPS 2026Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
  4. NeurIPS 2026When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
  5. NeurIPS 2026When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
  6. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
  7. NeurIPS 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
  8. NeurIPS 2025Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
  9. NeurIPS 2025Blackbox Model Provenance via Palimpsestic Membership Inference
  10. NeurIPS 2025Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
  11. NeurIPS 2025Competitive Advantage Attacks to Decentralized Federated Learning
  12. NeurIPS 2025Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations
  13. NeurIPS 2025Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
  14. NeurIPS 2025Deep Learning with Plausible Deniability
  15. NeurIPS 2025Distributional Adversarial Attacks and Training in Deep Hedging
  16. NeurIPS 2025Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization
  17. NeurIPS 2025Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
  18. NeurIPS 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
  19. NeurIPS 2025Exploring the limits of strong membership inference attacks on large language models
  20. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
  21. NeurIPS 2025From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
  22. NeurIPS 2025From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
  23. NeurIPS 2025Harnessing the Universal Geometry of Embeddings
  24. NeurIPS 2025LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
  25. NeurIPS 2025LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks
  26. NeurIPS 2025More effort is needed to protect pedestrian privacy in the era of AI
  27. NeurIPS 2025Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
  28. NeurIPS 2025On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
  29. NeurIPS 2025Optimal Best Arm Identification under Differential Privacy
  30. NeurIPS 2025Optimal Regret of Bandits under Differential Privacy
  31. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
  32. NeurIPS 2025Private Training Large-scale Models with Efficient DP-SGD
  33. NeurIPS 2025Probabilistic Reasoning with LLMs for Privacy Risk Estimation
  34. NeurIPS 2025Provable Watermarking for Data Poisoning Attacks
  35. NeurIPS 2025Reconstruction and Secrecy under Approximate Distance Queries
  36. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
  37. NeurIPS 2025Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
  38. NeurIPS 2025Setting $\varepsilon$ is not the Issue in Differential Privacy
  39. NeurIPS 2025SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
  40. NeurIPS 2025Statistical Parity with Exponential Weights
  41. NeurIPS 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
  42. NeurIPS 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
  43. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
  44. NeurIPS 2025Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
  45. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
  46. NeurIPS 2025TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks
  47. NeurIPS 2025Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
  48. NeurIPS 2025Vid-SME: Membership Inference Attacks against Large Video Understanding Models
  49. NeurIPS 2025What Really is a Member? Discrediting Membership Inference via Poisoning
  50. NeurIPS 2025⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers

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