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 25 篇，第 1 / 1 页

1. CVPR 2023Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
2. CVPR 2023CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search
3. CVPR 2023DartBlur: Privacy Preservation With Detection Artifact Suppression
4. CVPR 2023Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning
5. CVPR 2023Dynamic Generative Targeted Attacks With Pattern Injection
6. CVPR 2023Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks
7. CVPR 2023Enhancing the Self-Universality for Transferable Targeted Attacks
8. CVPR 2023Ensemble-Based Blackbox Attacks on Dense Prediction
9. CVPR 2023Learning To Generate Image Embeddings With User-Level Differential Privacy
10. CVPR 2023Make Landscape Flatter in Differentially Private Federated Learning
11. CVPR 2023Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks
12. CVPR 2023Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization
13. CVPR 2023Physical-World Optical Adversarial Attacks on 3D Face Recognition
14. CVPR 2023Privacy-Preserving Adversarial Facial Features
15. CVPR 2023Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses
16. CVPR 2023Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks
17. CVPR 2023Re-Thinking Model Inversion Attacks Against Deep Neural Networks
18. CVPR 2023Reinforcement Learning-Based Black-Box Model Inversion Attacks
19. CVPR 2023Robust Single Image Reflection Removal Against Adversarial Attacks
20. CVPR 2023SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization
21. CVPR 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition
22. CVPR 2023The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks
23. CVPR 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
24. CVPR 2023Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
25. CVPR 2023TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets

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。