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 36 篇，第 1 / 1 页

1. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
2. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
3. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
4. NeurIPS 2024BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
5. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
6. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
7. NeurIPS 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
8. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
9. NeurIPS 2024Data Free Backdoor Attacks
10. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
11. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
12. NeurIPS 2024Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
13. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
14. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
15. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
16. NeurIPS 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
17. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
18. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
19. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
20. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
21. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
22. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
23. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
24. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
25. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
26. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
27. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
28. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
29. NeurIPS 2024Stealth edits to large language models
30. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
31. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
32. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
33. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
34. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
35. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
36. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks

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。