隐私攻击论文趋势 2023–2026

主要结论

• 隐私攻击论文从 2023 年的 124 篇增长到 2026 年的 219 篇，三年间扩大到约 1.8 倍。
• ICLR 是发隐私攻击论文最多的会议，2023–2026 年共 262 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 80 篇。
• 在「联邦与隐私」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的安全聚合是 1.8 倍，隐私攻击是 1.8 倍。

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

• NeurIPS 2026A Private Empirical Defense Against Privacy Audits
• ICML 2026A Statistical Framework for Analyzing Specification Resistance to Learnware-Inversion Risks
• ICLR 2026(Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Privacy Assessment for LLMs
• CVPR 2026Out of Sight Out of Track Adversarial Attacks on Propagation-based
• NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
• ICML 2025A Certified Unlearning Approach without Access to Source Data
• ICLR 2025Adversarial Attacks on Data Attribution
• CVPR 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
• NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
• ICML 2024Collective Certified Robustness against Graph Injection Attacks
• ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
• CVPR 2024Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
• NeurIPS 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
• ICML 2023Data Poisoning Attacks Against Multimodal Encoders
• ICLR 2023Adversarial Attacks on Adversarial Bandits
• CVPR 2023Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
• NeurIPS 2026Adaptive Target-Charging with Privacy Filters and Individual Accounting
• ICML 2026How does Bayesian Sampling help Membership Inference Attacks?
• ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
• CVPR 2026Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image

全部隐私攻击论文

共 45 篇，第 1 / 1 页

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

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。