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 262 篇，第 2 / 6 页

51. ICLR 2026Memorization Through the Lens of Sample Gradients
52. ICLR 2026Mitigating Privacy Risk via Forget Set-Free Unlearning
53. ICLR 2026MOLM: Mixture of LoRA Markers
54. ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors
55. ICLR 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings
56. ICLR 2026No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
57. ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
58. ICLR 2026On the trade-off between expressivity and privacy in graph representation learning
59. ICLR 2026Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
60. ICLR 2026Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
61. ICLR 2026Optimizing Agent Planning for Security and Autonomy
62. ICLR 2026Optimizing Canaries for Privacy Auditing with Metagradient Descent
63. ICLR 2026Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
64. ICLR 2026Prediction with Expert Advice under Local Differential Privacy
65. ICLR 2026Privacy-Protected Causal Survival Analysis Under Distribution Shift
66. ICLR 2026Protection against Source Inference Attacks in Federated Learning
67. ICLR 2026Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
68. ICLR 2026RedacBench: Can AI Erase Your Secrets?
69. ICLR 2026Reducing information dependency does not cause training data privacy. Adversarially non-robust features do.
70. ICLR 2026Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
71. ICLR 2026RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility
72. ICLR 2026ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
73. ICLR 2026Robust Adversarial Attacks Against Unknown Disturbance via Inverse Gradient Sample
74. ICLR 2026Robust Spiking Neural Networks Against Adversarial Attacks
75. ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
76. ICLR 2026SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
77. ICLR 2026Sampling-aware Adversarial Attacks Against Large Language Models
78. ICLR 2026Searching for Privacy Risks in LLM Agents via Simulation
79. ICLR 2026Secure Inference for Diffusion Models via Unconditional Scores
80. ICLR 2026Selective Data Removal for Distributional Machine Unlearning
81. ICLR 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
82. ICLR 2026SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box Attacks
83. ICLR 2026Sharpness-Aware Machine Unlearning
84. ICLR 2026Skirting Additive Error Lower Bounds for Private Turnstile Streams
85. ICLR 2026SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
86. ICLR 2026SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
87. ICLR 2026Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion Models
88. ICLR 2026Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
89. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
90. ICLR 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
91. ICLR 2026Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
92. ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
93. ICLR 2026Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without Disclosure
94. ICLR 2026Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
95. ICLR 2026TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
96. ICLR 2026TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models
97. ICLR 2026Understanding and Improving Continuous LLM Adversarial Training via In-context Learning Theory
98. ICLR 2026Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
99. ICLR 2026VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
100. ICLR 2026WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols

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。