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 6 / 14 页

  1. ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
  2. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
  3. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
  4. ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
  5. ICLR 2025CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
  6. ICLR 2025CREAM: Consistency Regularized Self-Rewarding Language Models
  7. ICLR 2025DarkBench: Benchmarking Dark Patterns in Large Language Models
  8. ICLR 2025Democratic Training Against Universal Adversarial Perturbations
  9. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
  10. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
  11. ICLR 2025Does Training with Synthetic Data Truly Protect Privacy?
  12. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
  13. ICLR 2025Endless Jailbreaks with Bijection Learning
  14. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
  15. ICLR 2025EvA: Erasing Spurious Correlations with Activations
  16. ICLR 2025Exploring Local Memorization in Diffusion Models via Bright Ending Attention
  17. ICLR 2025Fair Clustering in the Sliding Window Model
  18. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
  19. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
  20. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
  21. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
  22. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
  23. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
  24. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
  25. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
  26. ICLR 2025Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks
  27. ICLR 2025Jailbreaking as a Reward Misspecification Problem
  28. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
  29. ICLR 2025Language Models are Advanced Anonymizers
  30. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
  31. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
  32. ICLR 2025Machine Unlearning via Simulated Oracle Matching
  33. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
  34. ICLR 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
  35. ICLR 2025Near-Exact Privacy Amplification for Matrix Mechanisms
  36. ICLR 2025On Evaluating the Durability of Safeguards for Open-Weight LLMs
  37. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
  38. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
  39. ICLR 2025Persistent Pre-training Poisoning of LLMs
  40. ICLR 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
  41. ICLR 2025Privacy Auditing of Large Language Models
  42. ICLR 2025Privacy-Aware Lifelong Learning
  43. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
  44. ICLR 2025Privately Counting Partially Ordered Data
  45. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
  46. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
  47. ICLR 2025Protecting against simultaneous data poisoning attacks
  48. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
  49. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
  50. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

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