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 175 篇，第 2 / 4 页

51. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
52. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
53. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
54. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
55. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
56. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
57. ICLR 2025Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks
58. ICLR 2025Jailbreaking as a Reward Misspecification Problem
59. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
60. ICLR 2025Language Models are Advanced Anonymizers
61. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
62. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
63. ICLR 2025Machine Unlearning via Simulated Oracle Matching
64. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
65. ICLR 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
66. ICLR 2025Near-Exact Privacy Amplification for Matrix Mechanisms
67. ICLR 2025On Evaluating the Durability of Safeguards for Open-Weight LLMs
68. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
69. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
70. ICLR 2025Persistent Pre-training Poisoning of LLMs
71. ICLR 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
72. ICLR 2025Privacy Auditing of Large Language Models
73. ICLR 2025Privacy-Aware Lifelong Learning
74. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
75. ICLR 2025Privately Counting Partially Ordered Data
76. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
77. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
78. ICLR 2025Protecting against simultaneous data poisoning attacks
79. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
80. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
81. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
82. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models
83. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
84. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
85. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
86. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
87. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
88. ICLR 2025Support is All You Need for Certified VAE Training
89. ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
90. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
91. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
92. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
93. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
94. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
95. ICLR 2025Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
96. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
97. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
98. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
99. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
100. ICLR 2025Variational Best-of-N Alignment

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。