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 180 篇，第 2 / 4 页

51. ICLR 2024Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
52. ICLR 2024Leave-one-out Distinguishability in Machine Learning
53. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
54. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
55. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
56. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
57. ICLR 2024Optimal transport based adversarial patch to leverage large scale attack transferability
58. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
59. ICLR 2024Privacy-Preserving In-Context Learning for Large Language Models
60. ICLR 2024PubDef: Defending Against Transfer Attacks From Public Models
61. ICLR 2024RAIN: Your Language Models Can Align Themselves without Finetuning
62. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
63. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
64. ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
65. ICLR 2024Sharpness-Aware Data Poisoning Attack
66. ICLR 2024Tangent Transformers for Composition,Privacy and Removal
67. ICLR 2024Teach LLMs to Phish: Stealing Private Information from Language Models
68. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
69. ICLR 2024The False Promise of Imitating Proprietary Language Models
70. ICLR 2024The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
71. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
72. ICLR 2024Towards Poisoning Fair Representations
73. ICLR 2024Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
74. ICLR 2024Universal Backdoor Attacks
75. ICLR 2024You Only Query Once: An Efficient Label-Only Membership Inference Attack
76. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
77. ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
78. ICML 2024AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
79. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
80. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
81. ICML 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
82. ICML 2024Collective Certified Robustness against Graph Injection Attacks
83. ICML 2024Data Poisoning Attacks against Conformal Prediction
84. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
85. ICML 2024Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
86. ICML 2024Fast Adversarial Attacks on Language Models In One GPU Minute
87. ICML 2024FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
88. ICML 2024Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy
89. ICML 2024Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
90. ICML 2024Low-Cost High-Power Membership Inference Attacks
91. ICML 2024Mean Estimation in the Add-Remove Model of Differential Privacy
92. ICML 2024Membership Inference Attacks on Diffusion Models via Quantile Regression
93. ICML 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
94. ICML 2024Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
95. ICML 2024Privacy Attacks in Decentralized Learning
96. ICML 2024Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
97. ICML 2024Privacy Profiles for Private Selection
98. ICML 2024Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent
99. ICML 2024Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
100. ICML 2024Private Truly-Everlasting Robust-Prediction

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。