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 209 篇，第 1 / 5 页

1. NeurIPS 2026A Private Empirical Defense Against Privacy Audits
2. NeurIPS 2026A Unified Framework for Adversary-Aware Differential Privacy Bounds
3. NeurIPS 2026Adaptive Target-Charging with Privacy Filters and Individual Accounting
4. NeurIPS 2026Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
5. NeurIPS 2026Assessing Per-Sample Membership Inference Vulnerability without Retraining
6. NeurIPS 2026Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
7. NeurIPS 2026Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
8. NeurIPS 2026Auditing Privacy Leakage in Tabular Foundation Model Embeddings
9. NeurIPS 2026Backdoor Attacks under Lossy Compression: From Failure to Reactivation and Adaptation
10. NeurIPS 2026Bayesian Low-Rank Posteriors for Scalable Membership Inference
11. NeurIPS 2026Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training
12. NeurIPS 2026Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
13. NeurIPS 2026Causal Evaluation of Membership Inference Attacks
14. NeurIPS 2026Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
15. NeurIPS 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
16. NeurIPS 2026Estimating Model-Level Membership Inference Vulnerability Without Reference Models
17. NeurIPS 2026Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning Diagnostics
18. NeurIPS 2026GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
19. NeurIPS 2026Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
20. NeurIPS 2026HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
21. NeurIPS 2026How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
22. NeurIPS 2026HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
23. NeurIPS 2026Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy
24. NeurIPS 2026Latent-space Attacks for Refusal Evasion in Language Models
25. NeurIPS 2026Learning Lotteries with Minimal Violations from Membership Queries
26. NeurIPS 2026Learning Robust Representations for Defending White-Box Adversarial Attacks in Continual Learning
27. NeurIPS 2026Learning the Signature of Memorization in Autoregressive Language Models
28. NeurIPS 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
29. NeurIPS 2026Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization
30. NeurIPS 2026MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
31. NeurIPS 2026MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks
32. NeurIPS 2026Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
33. NeurIPS 2026Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
34. NeurIPS 2026Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
35. NeurIPS 2026Privacy by Postprocessing the Discrete Laplace Mechanism
36. NeurIPS 2026Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning
37. NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
38. NeurIPS 2026Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
39. NeurIPS 2026Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
40. NeurIPS 2026Sequential Membership Inference Attacks
41. NeurIPS 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
42. NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
43. NeurIPS 2026SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
44. NeurIPS 2026Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
45. NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
46. NeurIPS 2026Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
47. NeurIPS 2026The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
48. NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
49. NeurIPS 2026Towards Universal Black-box Attacks on Graph Neural Networks
50. NeurIPS 2026TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs

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。