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 698 篇，第 4 / 14 页

151. ICML 2026Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
152. ICML 2026Persistent Backdoor Attacks in Class-Incremental Learning via Structural Invariant Anchoring
153. ICML 2026Persuasive Privacy
154. ICML 2026PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training
155. ICML 2026Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
156. ICML 2026Reconstructing Template-Memorized Images from Natural Prompts
157. ICML 2026Revisiting Asymmetries in Black-box Link Stealing against Graph Neural Networks
158. ICML 2026Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks
159. ICML 2026SORA: Free Second-Order Attacks in Fast Adversarial Training
160. ICML 2026The Hidden Risk: Membership Inference Attacks on Multimodal Federated Learning via Modality Imbalance
161. ICML 2026Training-Free Adversarial Robustness in Computational MRI
162. ICML 2026Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning Evaluations
163. ICML 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
164. ICML 2026Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path
165. NeurIPS 2026A Private Empirical Defense Against Privacy Audits
166. NeurIPS 2026A Unified Framework for Adversary-Aware Differential Privacy Bounds
167. NeurIPS 2026Adaptive Target-Charging with Privacy Filters and Individual Accounting
168. NeurIPS 2026Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
169. NeurIPS 2026Assessing Per-Sample Membership Inference Vulnerability without Retraining
170. NeurIPS 2026Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
171. NeurIPS 2026Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
172. NeurIPS 2026Auditing Privacy Leakage in Tabular Foundation Model Embeddings
173. NeurIPS 2026Backdoor Attacks under Lossy Compression: From Failure to Reactivation and Adaptation
174. NeurIPS 2026Bayesian Low-Rank Posteriors for Scalable Membership Inference
175. NeurIPS 2026Benchmarking Membership Privacy Risks in Preference-Based LLM Post-Training
176. NeurIPS 2026Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
177. NeurIPS 2026Causal Evaluation of Membership Inference Attacks
178. NeurIPS 2026Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
179. NeurIPS 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
180. NeurIPS 2026Estimating Model-Level Membership Inference Vulnerability Without Reference Models
181. NeurIPS 2026Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning Diagnostics
182. NeurIPS 2026GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
183. NeurIPS 2026Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
184. NeurIPS 2026HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
185. NeurIPS 2026How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
186. NeurIPS 2026HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
187. NeurIPS 2026Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy
188. NeurIPS 2026Latent-space Attacks for Refusal Evasion in Language Models
189. NeurIPS 2026Learning Lotteries with Minimal Violations from Membership Queries
190. NeurIPS 2026Learning Robust Representations for Defending White-Box Adversarial Attacks in Continual Learning
191. NeurIPS 2026Learning the Signature of Memorization in Autoregressive Language Models
192. NeurIPS 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
193. NeurIPS 2026Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge Regularization
194. NeurIPS 2026MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Privacy Evaluation of Language Model Agents
195. NeurIPS 2026MVPISplat: Multi-View Photometric Inconsistency for Defending 3D Gaussian Splatting Attacks
196. NeurIPS 2026Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
197. NeurIPS 2026Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
198. NeurIPS 2026Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
199. NeurIPS 2026Privacy by Postprocessing the Discrete Laplace Mechanism
200. NeurIPS 2026Privacy Meets Hierarchy: Differentially Private Distributed Trilevel Learning

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。