mlsanityData to 7 Oct 2026

FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases

arXiv 2302.14500 ↗First posted 28 Feb 2023cs.CR cs.AIcited by 7

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the trojaned model will have attacker-chosen abnormal behavior. Although many backdoor detection methods exist, most of them assume that the defender has access to a set of clean validation samples or samples with the trigger, which may not hold in some crucial real-world cases, e.g., the case where the defender is the maintainer of model-sharing platforms. Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger. The evaluation results on diverse datasets and model architectures show that FreeEagle is effective against various complex backdoor attacks, even outperforming some state-of-the-art non-data-free backdoor detection methods.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 37 of its 66 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

37 of 66 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning1 Aug
  2. 2021Hidden Backdoors in Human-Centric Language Models1 May
  3. 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification7 Mar

Other references · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  8. 2018How To Backdoor Federated Learningcited by 745
  9. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  10. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  11. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  12. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
22 more
  1. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  2. 2019On Evaluating Adversarial Robustnesscited by 442
  3. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  4. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  5. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  6. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  7. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  8. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 192
  9. 2020Blind Backdoors in Deep Learning Modelscited by 174
  10. 2019Universal Litmus Patterns: Revealing Backdoor Attacks in CNNscited by 143
  11. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 124
  12. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 121
  13. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 120
  14. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  15. 2020Graph Backdoorcited by 112
  16. 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 109
  17. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  18. 2020Trojaning Language Models for Fun and Profitcited by 80
  19. 2021Backdoor Pre-trained Models Can Transfer to Allcited by 79
  20. 2020DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentationcited by 75
  21. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 71
  22. 2019Difficulty-aware Meta-learning for Rare Disease Diagnosiscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 2.

7 papers.

  1. 2024CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Modelscited by 11
  2. 2025DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Datacited by 5
  3. 2024Model X-ray:Detecting Backdoored Models via Decision Boundarycited by 3
  4. 2024Composite Concept Extraction through Backdooringcited by 0
  5. 2025Defending against Backdoor Attacks via Module Switchingcited by 0
  6. 2026Lightweight and Fast Backdoor Model Detectioncited by 0
  7. 2026Fast and Lightweight Backdoor Detection via Head Random Probingcited by 0