Privacy Attacks papers, 2023–2026

Key findings

• Privacy Attacks went from 124 papers in 2023 to 219 in 2026, roughly 1.8x in three years.
• ICLR publishes the most Privacy Attacks work: 262 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 2 in 2023 to 80 in 2026.
• Among the 5 topics under Federated and Privacy, it ranks #1 by 2026 paper count; the fastest grower in the group, Secure Aggregation, is up 1.8x versus 1.8x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Privacy Attacks papers

138 papers, page 3 of 3

101. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
102. ICML 2024The Privacy Power of Correlated Noise in Decentralized Learning
103. ICML 2024Toward Availability Attacks in 3D Point Clouds
104. ICML 2024Trained Random Forests Completely Reveal your Dataset
105. ICML 2024Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
106. ICML 2024Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
107. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
108. ICML 2024Verifying message-passing neural networks via topology-based bounds tightening
109. ICML 2024Watermark Stealing in Large Language Models
110. ICML 2023Adversarial Parameter Attack on Deep Neural Networks
111. ICML 2023Algorithms for bounding contribution for histogram estimation under user-level privacy
112. ICML 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?
113. ICML 2023Bayesian Estimation of Differential Privacy
114. ICML 2023Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis
115. ICML 2023Concurrent Shuffle Differential Privacy Under Continual Observation
116. ICML 2023Data Poisoning Attacks Against Multimodal Encoders
117. ICML 2023Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
118. ICML 2023Differential Privacy has Bounded Impact on Fairness in Classification
119. ICML 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
120. ICML 2023Effectively Using Public Data in Privacy Preserving Machine Learning
121. ICML 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
122. ICML 2023Federated Linear Contextual Bandits with User-level Differential Privacy
123. ICML 2023From Robustness to Privacy and Back
124. ICML 2023Fully-Adaptive Composition in Differential Privacy
125. ICML 2023Graph Contrastive Backdoor Attacks
126. ICML 2023GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
127. ICML 2023HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
128. ICML 2023MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
129. ICML 2023Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
130. ICML 2023Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
131. ICML 2023Rethinking Backdoor Attacks
132. ICML 2023Run-off Election: Improved Provable Defense against Data Poisoning Attacks
133. ICML 2023Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance
134. ICML 2023Streaming Submodular Maximization with Differential Privacy
135. ICML 2023The Price of Differential Privacy under Continual Observation
136. ICML 2023The Saddle-Point Method in Differential Privacy
137. ICML 2023Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
138. ICML 2023Understanding Backdoor Attacks through the Adaptability Hypothesis

FAQ

How many Privacy Attacks papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

698 in total: 124 in 2023, 180 in 2024, 175 in 2025, 219 in 2026.

How many Privacy Attacks papers are at NeurIPS 2026?

NeurIPS 2026 has 55 Privacy Attacks papers, versus 45 the year before.

How many Privacy Attacks papers are at ICLR 2026?

ICLR 2026 has 102 Privacy Attacks papers, versus 83 the year before.

How many Privacy Attacks papers are at ICML 2026?

ICML 2026 has 38 Privacy Attacks papers, versus 29 the year before.

How many Privacy Attacks papers are at CVPR 2026?

CVPR 2026 has 24 Privacy Attacks papers, versus 18 the year before.

Which conference publishes the most Privacy Attacks papers?

ICLR, with 262 papers from 2023 to 2026.