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 124 篇，第 2 / 3 页

51. ICML 2023Algorithms for bounding contribution for histogram estimation under user-level privacy
52. ICML 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?
53. ICML 2023Bayesian Estimation of Differential Privacy
54. ICML 2023Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis
55. ICML 2023Concurrent Shuffle Differential Privacy Under Continual Observation
56. ICML 2023Data Poisoning Attacks Against Multimodal Encoders
57. ICML 2023Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
58. ICML 2023Differential Privacy has Bounded Impact on Fairness in Classification
59. ICML 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
60. ICML 2023Effectively Using Public Data in Privacy Preserving Machine Learning
61. ICML 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
62. ICML 2023Federated Linear Contextual Bandits with User-level Differential Privacy
63. ICML 2023From Robustness to Privacy and Back
64. ICML 2023Fully-Adaptive Composition in Differential Privacy
65. ICML 2023Graph Contrastive Backdoor Attacks
66. ICML 2023GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
67. ICML 2023HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
68. ICML 2023MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
69. ICML 2023Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
70. ICML 2023Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
71. ICML 2023Rethinking Backdoor Attacks
72. ICML 2023Run-off Election: Improved Provable Defense against Data Poisoning Attacks
73. ICML 2023Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance
74. ICML 2023Streaming Submodular Maximization with Differential Privacy
75. ICML 2023The Price of Differential Privacy under Continual Observation
76. ICML 2023The Saddle-Point Method in Differential Privacy
77. ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
78. ICML 2023Understanding Backdoor Attacks through the Adaptability Hypothesis
79. NeurIPS 2023$k$-Means Clustering with Distance-Based Privacy
80. NeurIPS 2023A Unified Detection Framework for Inference-Stage Backdoor Defenses
81. NeurIPS 2023A Unified Fast Gradient Clipping Framework for DP-SGD
82. NeurIPS 2023Adaptive Privacy Composition for Accuracy-first Mechanisms
83. NeurIPS 2023Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
84. NeurIPS 2023Batchnorm Allows Unsupervised Radial Attacks
85. NeurIPS 2023Blurred-Dilated Method for Adversarial Attacks
86. NeurIPS 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
87. NeurIPS 2023Bounding training data reconstruction in DP-SGD
88. NeurIPS 2023Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
89. NeurIPS 2023Counting Distinct Elements Under Person-Level Differential Privacy
90. NeurIPS 2023Data Minimization at Inference Time
91. NeurIPS 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
92. NeurIPS 2023Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
93. NeurIPS 2023Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
94. NeurIPS 2023Faster approximate subgraph counts with privacy
95. NeurIPS 2023FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
96. NeurIPS 2023Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
97. NeurIPS 2023GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference
98. NeurIPS 2023Gaussian Differential Privacy on Riemannian Manifolds
99. NeurIPS 2023Gaussian Membership Inference Privacy
100. NeurIPS 2023Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning 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。