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

63 papers, page 1 of 2

1. NeurIPS 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
2. NeurIPS 2024AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
3. NeurIPS 2024AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
4. NeurIPS 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
5. NeurIPS 2024Attack-Aware Noise Calibration for Differential Privacy
6. NeurIPS 2024Auditing Privacy Mechanisms via Label Inference Attacks
7. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
8. NeurIPS 2024Certified Machine Unlearning via Noisy Stochastic Gradient Descent
9. NeurIPS 2024Continual Counting with Gradual Privacy Expiration
10. NeurIPS 2024Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
11. NeurIPS 2024DAGER: Exact Gradient Inversion for Large Language Models
12. NeurIPS 2024Data Free Backdoor Attacks
13. NeurIPS 2024Deep Support Vectors
14. NeurIPS 2024Differentially Private Set Representations
15. NeurIPS 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
16. NeurIPS 2024Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
17. NeurIPS 2024Efficient Adversarial Training in LLMs with Continuous Attacks
18. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
19. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
20. NeurIPS 2024HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
21. NeurIPS 2024HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
22. NeurIPS 2024Improving Alignment and Robustness with Circuit Breakers
23. NeurIPS 2024Instance-Optimal Private Density Estimation in the Wasserstein Distance
24. NeurIPS 2024Instance-Specific Asymmetric Sensitivity in Differential Privacy
25. NeurIPS 2024Large Language Model Unlearning
26. NeurIPS 2024MALT Powers Up Adversarial Attacks
27. NeurIPS 2024Measuring Dejavu Memorization Efficiently
28. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
29. NeurIPS 2024Membership Inference Attacks against Large Vision-Language Models
30. NeurIPS 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
31. NeurIPS 2024Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
32. NeurIPS 2024On Differentially Private Subspace Estimation in a Distribution-Free Setting
33. NeurIPS 2024On provable privacy vulnerabilities of graph representations
34. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
35. NeurIPS 2024PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
36. NeurIPS 2024Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
37. NeurIPS 2024Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
38. NeurIPS 2024Private and Personalized Frequency Estimation in a Federated Setting
39. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
40. NeurIPS 2024PrivCirNet: Efficient Private Inference via Block Circulant Transformation
41. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
42. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
43. NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
44. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
45. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
46. NeurIPS 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
47. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
48. NeurIPS 2024Scalable DP-SGD: Shuffling vs. Poisson Subsampling
49. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
50. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

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.