后门攻击论文趋势 2023–2026

主要结论

• 后门攻击论文从 2023 年的 73 篇增长到 2026 年的 111 篇，三年间扩大到约 1.5 倍。
• NeurIPS 是发后门攻击论文最多的会议，2023–2026 年共 124 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 16 篇。
• 在「安全与可信」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的水印是 9.3 倍，后门攻击是 1.5 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部后门攻击论文

共 20 篇，第 1 / 1 页

1. ICLR 2026BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
2. ICLR 2026Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
3. ICLR 2026Black-Box Privacy Attacks on Shared Representations in Multitask Learning
4. ICLR 2026Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
5. ICLR 2026Defending against Backdoor Attacks via Module Switching
6. ICLR 2026Detecting Temporal Misalignment Attacks in Multimodal Fusion for Autonomous Driving
7. ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
8. ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
9. ICLR 2026Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
10. ICLR 2026No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
11. ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
12. ICLR 2026Protection against Source Inference Attacks in Federated Learning
13. ICLR 2026Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
14. ICLR 2026Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
15. ICLR 2026ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
16. ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
17. ICLR 2026STEDiff: Revealing the Spatial and Temporal Redundancy of Backdoor Attacks in Text-to-Image Diffusion Models
18. ICLR 2026Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP
19. ICLR 2026TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models
20. ICLR 2026Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models

常见问题

2023–2026 年四大会议一共有多少篇后门攻击论文？

共 381 篇，按年份分别是 2023 年 73 篇、2024 年 105 篇、2025 年 92 篇、2026 年 111 篇。

NeurIPS 2026 有多少篇后门攻击论文？

NeurIPS 2026 有 36 篇后门攻击论文，上一届是 31 篇。

ICLR 2026 有多少篇后门攻击论文？

ICLR 2026 有 20 篇后门攻击论文，上一届是 25 篇。

ICML 2026 有多少篇后门攻击论文？

ICML 2026 有 36 篇后门攻击论文，上一届是 17 篇。

CVPR 2026 有多少篇后门攻击论文？

CVPR 2026 有 19 篇后门攻击论文，上一届是 19 篇。

哪个会议的后门攻击论文最多？

NeurIPS，2023–2026 年共 124 篇。