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

175 papers, page 3 of 4

101. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
102. ICML 2025A Certified Unlearning Approach without Access to Source Data
103. ICML 2025A Closer Look at Backdoor Attacks on CLIP
104. ICML 2025Auditing Prompt Caching in Language Model APIs
105. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
106. ICML 2025Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
107. ICML 2025De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
108. ICML 2025Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms
109. ICML 2025EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
110. ICML 2025Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning
111. ICML 2025Fragments to Facts: Partial-Information Fragment Inference from LLMs
112. ICML 2025HyperNear: Unnoticeable Node Injection Attacks on Hypergraph Neural Networks
113. ICML 2025ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
114. ICML 2025Improving the Variance of Differentially Private Randomized Experiments through Clustering
115. ICML 2025Interpreting the Repeated Token Phenomenon in Large Language Models
116. ICML 2025Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
117. ICML 2025Leveraging Per-Instance Privacy for Machine Unlearning
118. ICML 2025MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
119. ICML 2025On Differential Privacy for Adaptively Solving Search Problems via Sketching
120. ICML 2025Position: Contextual Integrity is Inadequately Applied to Language Models
121. ICML 2025Privacy Attacks on Image AutoRegressive Models
122. ICML 2025Private Lossless Multiple Release
123. ICML 2025Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
124. ICML 2025Textual Unlearning Gives a False Sense of Unlearning
125. ICML 2025The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
126. ICML 2025The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
127. ICML 2025The Role of Randomness in Stability
128. ICML 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
129. ICML 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
130. ICML 2025Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
131. NeurIPS 2025A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
132. NeurIPS 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
133. NeurIPS 2025Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
134. NeurIPS 2025Blackbox Model Provenance via Palimpsestic Membership Inference
135. NeurIPS 2025Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
136. NeurIPS 2025Competitive Advantage Attacks to Decentralized Federated Learning
137. NeurIPS 2025Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations
138. NeurIPS 2025Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
139. NeurIPS 2025Deep Learning with Plausible Deniability
140. NeurIPS 2025Distributional Adversarial Attacks and Training in Deep Hedging
141. NeurIPS 2025Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization
142. NeurIPS 2025Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
143. NeurIPS 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
144. NeurIPS 2025Exploring the limits of strong membership inference attacks on large language models
145. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
146. NeurIPS 2025From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
147. NeurIPS 2025From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
148. NeurIPS 2025Harnessing the Universal Geometry of Embeddings
149. NeurIPS 2025LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
150. NeurIPS 2025LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks

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.