Backdoor Attacks papers, 2023–2026

Key findings

• Backdoor Attacks went from 73 papers in 2023 to 111 in 2026, roughly 1.5x in three years.
• NeurIPS publishes the most Backdoor Attacks work: 124 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 0 in 2023 to 16 in 2026.
• Among the 5 topics under Security and Trust, it ranks #2 by 2026 paper count; the fastest grower in the group, Watermarking, is up 9.3x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
• ICML 2026Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning
• ICLR 2026Defending against Backdoor Attacks via Module Switching
• CVPR 2026Eliminate Distance Differences Induced by Backdoor Attacks Layer-Selective Training and
• NeurIPS 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
• ICML 2025A Closer Look at Backdoor Attacks on CLIP
• ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
• CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
• NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
• ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
• ICLR 2024Adversarial Feature Map Pruning for Backdoor
• CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
• NeurIPS 2023A Unified Detection Framework for Inference-Stage Backdoor Defenses
• ICML 2023Data Poisoning Attacks Against Multimodal Encoders
• ICLR 2023Adversarial Attacks on Adversarial Bandits
• CVPR 2023Architectural Backdoors in Neural Networks
• NeurIPS 2026AI Models Can Provably Hide Arbitrary Capabilities
• ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
• ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
• CVPR 2026Logit-Margin Repulsion for Backdoor Defense

All Backdoor Attacks papers

105 papers, page 1 of 3

1. CVPR 2024Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
2. CVPR 2024Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models
3. CVPR 2024Backdoor Defense via Test-Time Detecting and Repairing
4. CVPR 2024BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
5. CVPR 2024BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
6. CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
7. CVPR 2024GLOW: Global Layout Aware Attacks on Object Detection
8. CVPR 2024Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
9. CVPR 2024LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
10. CVPR 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
11. CVPR 2024Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers
12. CVPR 2024One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning
13. CVPR 2024Overload: Latency Attacks on Object Detection for Edge Devices
14. CVPR 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
15. CVPR 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
16. CVPR 2024Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
17. CVPR 2024Re-thinking Data Availability Attacks Against Deep Neural Networks
18. CVPR 2024Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
19. ICLR 2024Adversarial Feature Map Pruning for Backdoor
20. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
21. ICLR 2024Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
22. ICLR 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
23. ICLR 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
24. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
25. ICLR 2024BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
26. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
27. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
28. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
29. ICLR 2024Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
30. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
31. ICLR 2024Influencer Backdoor Attack on Semantic Segmentation
32. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
33. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
34. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
35. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
36. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
37. ICLR 2024Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
38. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
39. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
40. ICLR 2024Safe and Robust Watermark Injection with a Single OoD Image
41. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
42. ICLR 2024Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
43. ICLR 2024Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
44. ICLR 2024Universal Backdoor Attacks
45. ICLR 2024VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
46. ICML 2024A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
47. ICML 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
48. ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
49. ICML 2024Causality Based Front-door Defense Against Backdoor Attack on Language Models
50. ICML 2024Data Poisoning Attacks against Conformal Prediction

FAQ

How many Backdoor Attacks papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

381 in total: 73 in 2023, 105 in 2024, 92 in 2025, 111 in 2026.

How many Backdoor Attacks papers are at NeurIPS 2026?

NeurIPS 2026 has 36 Backdoor Attacks papers, versus 31 the year before.

How many Backdoor Attacks papers are at ICLR 2026?

ICLR 2026 has 20 Backdoor Attacks papers, versus 25 the year before.

How many Backdoor Attacks papers are at ICML 2026?

ICML 2026 has 36 Backdoor Attacks papers, versus 17 the year before.

How many Backdoor Attacks papers are at CVPR 2026?

CVPR 2026 has 19 Backdoor Attacks papers, versus 19 the year before.

Which conference publishes the most Backdoor Attacks papers?

NeurIPS, with 124 papers from 2023 to 2026.