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

89 papers, page 1 of 2

1. CVPR 2026AdvFM Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial
2. CVPR 2026Black-box Membership Inference Attacks on the Pre-training Data of Image-generation
3. CVPR 2026Eliminate Distance Differences Induced by Backdoor Attacks Layer-Selective Training and
4. CVPR 2026FedMOP Achieving Enhanced Privacy and Performance in Federated Learning via
5. CVPR 2026FORCE Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
6. CVPR 2026Fractal Camouflage A Bio-Inspired Approach for Multi-Scale Adversarial Attacks in
7. CVPR 2026LDP-Slicing Local Differential Privacy for Images via Randomized Bit-Plane Slicing
8. CVPR 2026No Way To Steal My Face Proactive Defense Against Identity-Preserving
9. CVPR 2026Omni-Attack Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs
10. CVPR 2026Out of Sight Out of Track Adversarial Attacks on Propagation-based
11. CVPR 2026Personalized Federated Training of Diffusion Models with Privacy Guarantees
12. CVPR 2026PrivSynth Alternating and Control-Based Optimization for Privacy and Utility in
13. CVPR 2026Protego User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint
14. CVPR 2026RaPA Enhancing Transferable Targeted Attacks via Random Parameter Pruning
15. CVPR 2026RemedyGS Defend 3D Gaussian Splatting Against Computation Cost Attacks
16. CVPR 2026Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image
17. CVPR 2026SEBA Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
18. CVPR 2026Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
19. CVPR 2026Towards Cross-Modal Preservation Consistency and Alignment for Privacy-Preserving Visible-Infrared Person
20. CVPR 2026Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
21. CVPR 2026Towards Stealthy and Effective Backdoor Attacks on Lane Detection A
22. CVPR 2026V-Attack Targeting Disentangled Value Features for Controllable Adversarial Attacks on
23. CVPR 2026VCP-Attack Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large
24. CVPR 2026When Robots Obey the Patch Universal Transferable Patch Attacks on
25. CVPR 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
26. CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
27. CVPR 2025Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
28. CVPR 2025CDI: Copyrighted Data Identification in Diffusion Models
29. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
30. CVPR 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
31. CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
32. CVPR 2025Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
33. CVPR 2025FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
34. CVPR 2025From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
35. CVPR 2025Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization
36. CVPR 2025Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
37. CVPR 2025Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation
38. CVPR 2025Improving Transferable Targeted Attacks with Feature Tuning Mixup
39. CVPR 2025Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
40. CVPR 2025Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
41. CVPR 2025Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
42. CVPR 2025Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models
43. CVPR 2024Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models
44. CVPR 2024BrainWash: A Poisoning Attack to Forget in Continual Learning
45. CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
46. CVPR 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
47. CVPR 2024Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
48. CVPR 2024Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
49. CVPR 2024LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
50. CVPR 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned 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.