mlsanityData to 7 Oct 2026

AGNES: Abstraction-guided Framework for Deep Neural Networks Security

arXiv 2311.04009 ↗First posted 7 Nov 2023cs.LG cs.CR cs.CVcited by 0

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

Abstract (arXiv)

Deep Neural Networks (DNNs) are becoming widespread, particularly in safety-critical areas. One prominent application is image recognition in autonomous driving, where the correct classification of objects, such as traffic signs, is essential for safe driving. Unfortunately, DNNs are prone to backdoors, meaning that they concentrate on attributes of the image that should be irrelevant for their correct classification. Backdoors are integrated into a DNN during training, either with malicious intent (such as a manipulated training process, because of which a yellow sticker always leads to a traffic sign being recognised as a stop sign) or unintentional (such as a rural background leading to any traffic sign being recognised as animal crossing, because of biased training data). In this paper, we introduce AGNES, a tool to detect backdoors in DNNs for image recognition. We discuss the principle approach on which AGNES is based. Afterwards, we show that our tool performs better than many state-of-the-art methods for multiple relevant case studies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 17 of its 27 references that are in the map. First posted on arXiv 7 Nov 2023.

Builds on

17 of 27 references.

References · 17

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  4. 2020Backdoor Learning: A Surveycited by 412
  5. 2019Hidden Trigger Backdoor Attackscited by 359
  6. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  7. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  8. 2019Universal Litmus Patterns: Revealing Backdoor Attacks in CNNscited by 143
  9. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  10. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  11. 2021Backdoor Scanning for Deep Neural Networks through K-Arm Optimizationcited by 96
  12. 2020One-pixel Signature: Characterizing CNN Models for Backdoor Detectioncited by 34
5 more
  1. 2020DeepAbstract: Neural Network Abstraction for Accelerating Verificationcited by 31
  2. 2017An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Softwarecited by 26
  3. 2017An Equivalence of Fully Connected Layer and Convolutional Layercited by 14
  4. 2022Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applicationscited by 6
  5. 2022Backdoor Mitigation in Deep Neural Networks via Strategic Retrainingcited by 1

Built on by

Not cited yet.