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

262 papers, page 4 of 6

151. ICLR 2025On Evaluating the Durability of Safeguards for Open-Weight LLMs
152. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
153. ICLR 2025Optimality of Matrix Mechanism on $\ell_p^p$-metric
154. ICLR 2025Persistent Pre-training Poisoning of LLMs
155. ICLR 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
156. ICLR 2025Privacy Auditing of Large Language Models
157. ICLR 2025Privacy-Aware Lifelong Learning
158. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
159. ICLR 2025Privately Counting Partially Ordered Data
160. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
161. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
162. ICLR 2025Protecting against simultaneous data poisoning attacks
163. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
164. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
165. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
166. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models
167. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
168. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
169. ICLR 2025Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions
170. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
171. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
172. ICLR 2025Support is All You Need for Certified VAE Training
173. ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
174. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
175. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
176. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
177. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
178. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
179. ICLR 2025Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
180. ICLR 2025Training Robust Ensembles Requires Rethinking Lipschitz Continuity
181. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
182. ICLR 2025Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
183. ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
184. ICLR 2025Variational Best-of-N Alignment
185. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
186. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
187. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
188. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
189. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
190. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
191. ICLR 2024Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
192. ICLR 2024Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
193. ICLR 2024Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
194. ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
195. ICLR 2024Deceptive Fairness Attacks on Graphs via Meta Learning
196. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
197. ICLR 2024Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
198. ICLR 2024DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
199. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
200. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

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.