隐私攻击论文趋势 2023–2026
成员推断等
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 698 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 46 | 24 | 29 | 25 | 124 |
| 2024 | 63 | 53 | 42 | 22 | 180 |
| 2025 | 45 | 83 | 29 | 18 | 175 |
| 2026 | 55 | 102 | 38 | 24 | 219 |
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 219 篇，第 5 / 5 页
- NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
- NeurIPS 2026Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
- NeurIPS 2026Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
- NeurIPS 2026Sequential Membership Inference Attacks
- NeurIPS 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
- NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- NeurIPS 2026SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
- NeurIPS 2026Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
- NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
- NeurIPS 2026Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
- NeurIPS 2026The Price of Locality in Label Privacy: Optimal Rates for Classification and Regression
- NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
- NeurIPS 2026Towards Universal Black-box Attacks on Graph Neural Networks
- NeurIPS 2026TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
- NeurIPS 2026TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
- NeurIPS 2026Training-Based Backdoors Are Not Cryptographic
- NeurIPS 2026Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
- NeurIPS 2026When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
- NeurIPS 2026When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查隐私攻击在 ICLR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "privacy-attacks"}
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。