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 3 / 6 页

101. ICLR 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining
102. ICLR 2026Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
103. ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
104. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
105. ICLR 2025ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification
106. ICLR 2025Adversarial Attacks on Data Attribution
107. ICLR 2025Adversarial Machine Unlearning
108. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
109. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
110. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
111. ICLR 2025Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
112. ICLR 2025Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
113. ICLR 2025BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
114. ICLR 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
115. ICLR 2025Can a Large Language Model be a Gaslighter?
116. ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
117. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
118. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
119. ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
120. ICLR 2025CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
121. ICLR 2025CREAM: Consistency Regularized Self-Rewarding Language Models
122. ICLR 2025DarkBench: Benchmarking Dark Patterns in Large Language Models
123. ICLR 2025Democratic Training Against Universal Adversarial Perturbations
124. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
125. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
126. ICLR 2025Does Training with Synthetic Data Truly Protect Privacy?
127. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
128. ICLR 2025Endless Jailbreaks with Bijection Learning
129. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
130. ICLR 2025EvA: Erasing Spurious Correlations with Activations
131. ICLR 2025Exploring Local Memorization in Diffusion Models via Bright Ending Attention
132. ICLR 2025Fair Clustering in the Sliding Window Model
133. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
134. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
135. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
136. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
137. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
138. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
139. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
140. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
141. ICLR 2025Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks
142. ICLR 2025Jailbreaking as a Reward Misspecification Problem
143. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
144. ICLR 2025Language Models are Advanced Anonymizers
145. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
146. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
147. ICLR 2025Machine Unlearning via Simulated Oracle Matching
148. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
149. ICLR 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
150. ICLR 2025Near-Exact Privacy Amplification for Matrix Mechanisms

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。