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

180 papers, page 4 of 4

151. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
152. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
153. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
154. NeurIPS 2024Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
155. NeurIPS 2024Private and Personalized Frequency Estimation in a Federated Setting
156. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
157. NeurIPS 2024PrivCirNet: Efficient Private Inference via Block Circulant Transformation
158. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
159. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
160. NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
161. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
162. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
163. NeurIPS 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
164. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
165. NeurIPS 2024Scalable DP-SGD: Shuffling vs. Poisson Subsampling
166. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
167. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
168. NeurIPS 2024SPEAR: Exact Gradient Inversion of Batches in Federated Learning
169. NeurIPS 2024Stealth edits to large language models
170. NeurIPS 2024SuperDeepFool: a new fast and accurate minimal adversarial attack
171. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
172. NeurIPS 2024The Limits of Differential Privacy in Online Learning
173. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
174. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
175. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
176. NeurIPS 2024United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
177. NeurIPS 2024Watermarking Makes Language Models Radioactive
178. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
179. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
180. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

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.