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 87 篇，第 2 / 2 页

51. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
52. ICLR 2024BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
53. ICLR 2024Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
54. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
55. ICLR 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
56. ICLR 2024Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
57. ICLR 2024Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
58. ICLR 2024Influencer Backdoor Attack on Semantic Segmentation
59. ICLR 2024Leveraging Optimization for Adaptive Attacks on Image Watermarks
60. ICLR 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
61. ICLR 2024On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
62. ICLR 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
63. ICLR 2024Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
64. ICLR 2024Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
65. ICLR 2024Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
66. ICLR 2024Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
67. ICLR 2024Safe and Robust Watermark Injection with a Single OoD Image
68. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
69. ICLR 2024Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
70. ICLR 2024Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
71. ICLR 2024Universal Backdoor Attacks
72. ICLR 2024VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
73. ICLR 2023Adversarial Attacks on Adversarial Bandits
74. ICLR 2023Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
75. ICLR 2023Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
76. ICLR 2023Distilling Cognitive Backdoor Patterns within an Image
77. ICLR 2023Effective passive membership inference attacks in federated learning against overparameterized models
78. ICLR 2023Few-shot Backdoor Attacks via Neural Tangent Kernels
79. ICLR 2023FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
80. ICLR 2023Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
81. ICLR 2023Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
82. ICLR 2023Revisiting the Assumption of Latent Separability for Backdoor Defenses
83. ICLR 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
84. ICLR 2023The Dark Side of AutoML: Towards Architectural Backdoor Search
85. ICLR 2023Towards Robustness Certification Against Universal Perturbations
86. ICLR 2023TrojText: Test-time Invisible Textual Trojan Insertion
87. ICLR 2023UNICORN: A Unified Backdoor Trigger Inversion Framework

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。