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 53 篇，第 1 / 2 页

1. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
2. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
3. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
4. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
5. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
6. ICLR 2024Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
7. ICLR 2024Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
8. ICLR 2024Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
9. ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
10. ICLR 2024Deceptive Fairness Attacks on Graphs via Meta Learning
11. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
12. ICLR 2024Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
13. ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
14. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
15. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
16. ICLR 2024Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
17. ICLR 2024FedInverse: Evaluating Privacy Leakage in Federated Learning
18. ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
19. ICLR 2024Fixed-Budget Differentially Private Best Arm Identification
20. ICLR 2024GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
21. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
22. ICLR 2024Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
23. ICLR 2024Improving LoRA in Privacy-preserving Federated Learning
24. ICLR 2024IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
25. ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
26. ICLR 2024LabelDP-Pro: Learning with Label Differential Privacy via Projections
27. ICLR 2024Language Model Detectors Are Easily Optimized Against
28. ICLR 2024Language Model Inversion
29. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
30. ICLR 2024Leave-one-out Distinguishability in Machine Learning
31. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
32. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
33. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
34. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
35. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
36. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
37. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
38. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
39. ICLR 2024RAIN: Your Language Models Can Align Themselves without Finetuning
40. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
41. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
42. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
43. ICLR 2024Sharpness-Aware Data Poisoning Attack
44. ICLR 2024Tangent Transformers for Composition,Privacy and Removal
45. ICLR 2024Teach LLMs to Phish: Stealing Private Information from Language Models
46. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
47. ICLR 2024The False Promise of Imitating Proprietary Language Models
48. ICLR 2024The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
49. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
50. ICLR 2024Towards Poisoning Fair Representations

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。