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 3 / 5 页

101. ICLR 2026Sampling-aware Adversarial Attacks Against Large Language Models
102. ICLR 2026Searching for Privacy Risks in LLM Agents via Simulation
103. ICLR 2026Secure Inference for Diffusion Models via Unconditional Scores
104. ICLR 2026Selective Data Removal for Distributional Machine Unlearning
105. ICLR 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
106. ICLR 2026SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box Attacks
107. ICLR 2026Sharpness-Aware Machine Unlearning
108. ICLR 2026Skirting Additive Error Lower Bounds for Private Turnstile Streams
109. ICLR 2026SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
110. ICLR 2026SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
111. ICLR 2026Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion Models
112. ICLR 2026Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
113. ICLR 2026TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
114. ICLR 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
115. ICLR 2026Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
116. ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
117. ICLR 2026Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without Disclosure
118. ICLR 2026Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
119. ICLR 2026TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
120. ICLR 2026TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models
121. ICLR 2026Understanding and Improving Continuous LLM Adversarial Training via In-context Learning Theory
122. ICLR 2026Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
123. ICLR 2026VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
124. ICLR 2026WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
125. ICLR 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining
126. ICLR 2026Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
127. ICML 2026A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills
128. ICML 2026A Statistical Framework for Analyzing Specification Resistance to Learnware-Inversion Risks
129. ICML 2026Adversarial Attacks and Robust Training for Hypergraph Neural Networks
130. ICML 2026AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
131. ICML 2026AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
132. ICML 2026An Empirical Study on the Resilience of Partial Merging to Model Clone Attacks
133. ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
134. ICML 2026Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
135. ICML 2026CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
136. ICML 2026DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
137. ICML 2026Efficient privacy loss accounting for subsampling and random allocation
138. ICML 2026Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
139. ICML 2026Fast and Near-Optimal Algorithms for Private Hypothesis Selection
140. ICML 2026From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
141. ICML 2026Gradient Inversion Attacks Beyond SGD
142. ICML 2026How does Bayesian Sampling help Membership Inference Attacks?
143. ICML 2026Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
144. ICML 2026Membership Inference Attacks for Unseen Classes
145. ICML 2026MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
146. ICML 2026Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
147. ICML 2026Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
148. ICML 2026New Wide-Net-Casting Jailbreak Attacks Risk Large Models
149. ICML 2026On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
150. ICML 2026OptiFluence: Principled Design of Privacy Canaries

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。