mlsanityData to 7 Oct 2026

SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach

arXiv 2505.14531 ↗First posted 20 May 2025cs.LGcited by 2

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

Abstract (arXiv)

Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purification approach resorting to the classic Ising model. To date, existing trigger detection/removal studies usually require to know the detailed knowledge of target model in advance, access to a large number of clean samples or even model-retraining authorization, which brings the huge inconvenience for practical applications, especially inaccessible to target model. An ideal countermeasure ought to eliminate the implanted trigger without regarding whatever the target models are. To this end, a lightweight and black-box defense approach SifterNet is proposed through leveraging the memorization-association functionality of Hopfield network, by which the triggers of input samples can be effectively purified in a proper manner. The main novelty of our proposed approach lies in the introduction of ideology of Ising model. Extensive experiments also validate the effectiveness of our approach in terms of proper trigger purification and high accuracy achievement, and compared to the state-of-the-art baselines under several commonly-used datasets, our SiferNet has a significant superior performance.

Key facts. Cited by 2 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 20 of its 38 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

20 of 38 references.

References · 20

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  3. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  4. 2020Hopfield Networks is All You Needcited by 461
  5. 2018Spectral Signatures in Backdoor Attackscited by 457
  6. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  7. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  8. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  9. 2022Backdoor Defense via Decoupling the Training Processcited by 149
  10. 2018SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systemscited by 148
  11. 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 123
  12. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 121
8 more
  1. 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistencycited by 93
  2. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 71
  3. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 62
  4. 2023Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistencycited by 45
  5. 2022Towards A Proactive ML Approach for Detecting Backdoor Poison Samplescited by 40
  6. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  7. 2024BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learningcited by 17
  8. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHEcited by 0
  2. 2026Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networkscited by 0