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 219 篇，第 2 / 5 页

51. ICLR 2026Dual-Space Smoothness for Robust and Balanced LLM Unlearning
52. ICLR 2026Efficient Adversarial Attacks on High-dimensional Offline Bandits
53. ICLR 2026EigenBench: A Comparative Behavioral Measure of Value Alignment
54. ICLR 2026Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
55. ICLR 2026EvA: Evolutionary Attacks on Graphs
56. ICLR 2026Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made Practical
57. ICLR 2026Federated Learning of Quantile Inference under Local Differential Privacy
58. ICLR 2026Federated Learning with Profile Mapping under Distribution Shifts and Drifts
59. ICLR 2026Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
60. ICLR 2026Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry
61. ICLR 2026Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
62. ICLR 2026Ghost in the Cloud: Your Geo-Distributed Large Language Models Training is Easily Manipulated
63. ICLR 2026GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
64. ICLR 2026Hubble: a Model Suite to Advance the Study of LLM Memorization
65. ICLR 2026INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
66. ICLR 2026Jailbreak Transferability Emerges from Shared Representations
67. ICLR 2026JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe
68. ICLR 2026JULI: Jailbreak Large Language Models by Self-Introspection
69. ICLR 2026Label Smoothing Improves Machine Unlearning
70. ICLR 2026Language Models are Injective and Hence Invertible
71. ICLR 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
72. ICLR 2026Learning to Lie: Adversarial Attacks on Human-AI Teams and LLMs
73. ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
74. ICLR 2026Membership Privacy Risks of Sharpness Aware Minimization
75. ICLR 2026Memorization Through the Lens of Sample Gradients
76. ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
77. ICLR 2026MOLM: Mixture of LoRA Markers
78. ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors
79. ICLR 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings
80. ICLR 2026No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
81. ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
82. ICLR 2026On the trade-off between expressivity and privacy in graph representation learning
83. ICLR 2026Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
84. ICLR 2026Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
85. ICLR 2026Optimizing Agent Planning for Security and Autonomy
86. ICLR 2026Optimizing Canaries for Privacy Auditing with Metagradient Descent
87. ICLR 2026Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
88. ICLR 2026Prediction with Expert Advice under Local Differential Privacy
89. ICLR 2026Privacy-Protected Causal Survival Analysis Under Distribution Shift
90. ICLR 2026Protection against Source Inference Attacks in Federated Learning
91. ICLR 2026Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
92. ICLR 2026RedacBench: Can AI Erase Your Secrets?
93. ICLR 2026Reducing information dependency does not cause training data privacy. Adversarially non-robust features do.
94. ICLR 2026Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
95. ICLR 2026RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility
96. ICLR 2026ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
97. ICLR 2026Robust Adversarial Attacks Against Unknown Disturbance via Inverse Gradient Sample
98. ICLR 2026Robust Spiking Neural Networks Against Adversarial Attacks
99. ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
100. ICLR 2026SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak 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。