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 38 篇，第 1 / 1 页

1. ICML 2026A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills
2. ICML 2026A Statistical Framework for Analyzing Specification Resistance to Learnware-Inversion Risks
3. ICML 2026Adversarial Attacks and Robust Training for Hypergraph Neural Networks
4. ICML 2026AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
5. ICML 2026AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
6. ICML 2026An Empirical Study on the Resilience of Partial Merging to Model Clone Attacks
7. ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
8. ICML 2026Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
9. ICML 2026CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
10. ICML 2026DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
11. ICML 2026Efficient privacy loss accounting for subsampling and random allocation
12. ICML 2026Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
13. ICML 2026Fast and Near-Optimal Algorithms for Private Hypothesis Selection
14. ICML 2026From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
15. ICML 2026Gradient Inversion Attacks Beyond SGD
16. ICML 2026How does Bayesian Sampling help Membership Inference Attacks?
17. ICML 2026Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
18. ICML 2026Membership Inference Attacks for Unseen Classes
19. ICML 2026MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
20. ICML 2026Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
21. ICML 2026Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
22. ICML 2026New Wide-Net-Casting Jailbreak Attacks Risk Large Models
23. ICML 2026On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
24. ICML 2026OptiFluence: Principled Design of Privacy Canaries
25. ICML 2026Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
26. ICML 2026Persistent Backdoor Attacks in Class-Incremental Learning via Structural Invariant Anchoring
27. ICML 2026Persuasive Privacy
28. ICML 2026PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training
29. ICML 2026Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
30. ICML 2026Reconstructing Template-Memorized Images from Natural Prompts
31. ICML 2026Revisiting Asymmetries in Black-box Link Stealing against Graph Neural Networks
32. ICML 2026Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks
33. ICML 2026SORA: Free Second-Order Attacks in Fast Adversarial Training
34. ICML 2026The Hidden Risk: Membership Inference Attacks on Multimodal Federated Learning via Modality Imbalance
35. ICML 2026Training-Free Adversarial Robustness in Computational MRI
36. ICML 2026Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning Evaluations
37. ICML 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
38. ICML 2026Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path

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。