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

92 papers, page 1 of 2

1. CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
2. CVPR 2025Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
3. CVPR 2025Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices
4. CVPR 2025DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders
5. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
6. CVPR 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
7. CVPR 2025EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection
8. CVPR 2025Improving Transferable Targeted Attacks with Feature Tuning Mixup
9. CVPR 2025Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
10. CVPR 2025Invisible Backdoor Attack against Self-supervised Learning
11. CVPR 2025Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
12. CVPR 2025Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
13. CVPR 2025PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
14. CVPR 2025Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
15. CVPR 2025Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
16. CVPR 2025Test-Time Backdoor Detection for Object Detection Models
17. CVPR 2025UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
18. CVPR 2025Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models
19. CVPR 2025Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation
20. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
21. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
22. ICLR 2025Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
23. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
24. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
25. ICLR 2025Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
26. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
27. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
28. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
29. ICLR 2025Detecting Backdoor Samples in Contrastive Language Image Pretraining
30. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
31. ICLR 2025Energy-based Backdoor Defense Against Federated Graph Learning
32. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
33. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
34. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
35. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
36. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
37. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
38. ICLR 2025Protecting against simultaneous data poisoning attacks
39. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
40. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
41. ICLR 2025RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
42. ICLR 2025Robustness Inspired Graph Backdoor Defense
43. ICLR 2025UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping
44. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
45. ICML 2025A Closer Look at Backdoor Attacks on CLIP
46. ICML 2025Adversarial Inception Backdoor Attacks against Reinforcement Learning
47. ICML 2025Backdoor Attacks in Token Selection of Attention Mechanism
48. ICML 2025Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
49. ICML 2025Circumventing Backdoor Space via Weight Symmetry
50. ICML 2025CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

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.