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 42 篇，第 1 / 1 页

1. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
2. ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
3. ICML 2024AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
4. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
5. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
6. ICML 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
7. ICML 2024Collective Certified Robustness against Graph Injection Attacks
8. ICML 2024Data Poisoning Attacks against Conformal Prediction
9. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
10. ICML 2024Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
11. ICML 2024Fast Adversarial Attacks on Language Models In One GPU Minute
12. ICML 2024FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
13. ICML 2024Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy
14. ICML 2024Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
15. ICML 2024Low-Cost High-Power Membership Inference Attacks
16. ICML 2024Mean Estimation in the Add-Remove Model of Differential Privacy
17. ICML 2024Membership Inference Attacks on Diffusion Models via Quantile Regression
18. ICML 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
19. ICML 2024Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
20. ICML 2024Privacy Attacks in Decentralized Learning
21. ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
22. ICML 2024Privacy Profiles for Private Selection
23. ICML 2024Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent
24. ICML 2024Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
25. ICML 2024Private Truly-Everlasting Robust-Prediction
26. ICML 2024Provable Privacy with Non-Private Pre-Processing
27. ICML 2024Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
28. ICML 2024Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas
29. ICML 2024Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD
30. ICML 2024Revisiting Character-level Adversarial Attacks for Language Models
31. ICML 2024Shifted Interpolation for Differential Privacy
32. ICML 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
33. ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
34. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
35. ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
36. ICML 2024Toward Availability Attacks in 3D Point Clouds
37. ICML 2024Trained Random Forests Completely Reveal your Dataset
38. ICML 2024Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
39. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
40. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
41. ICML 2024Verifying message-passing neural networks via topology-based bounds tightening
42. ICML 2024Watermark Stealing in Large Language Models

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。