mlsanityData to 14 Oct 2026

Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping

arXiv 2511.13356 ↗First posted 17 Nov 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks pose severe threats to machine learning systems, prompting extensive research in this area. However, most existing work focuses on single-target All-to-One (A2O) attacks, overlooking the more complex All-to-X (A2X) attacks with multiple target classes, which are often assumed to have low attack success rates. In this paper, we first demonstrate that A2X attacks are robust against state-of-the-art defenses. We then propose a novel attack strategy that enhances the success rate of A2X attacks while maintaining robustness by optimizing grouping and target class assignment mechanisms. Our method improves the attack success rate by up to 28%, with average improvements of 6.7%, 16.4%, 14.1% on CIFAR10, CIFAR100, and Tiny-ImageNet, respectively. We anticipate that this study will raise awareness of A2X attacks and stimulate further research in this under-explored area. Our code is available at https://github.com/kazefjj/A2X-backdoor .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

24 of 42 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  6. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  7. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  8. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  9. 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 533
  10. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  11. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  12. 2020Input-Aware Dynamic Backdoor Attackcited by 313
12 more
  1. 2019Label-Consistent Backdoor Attackscited by 296
  2. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 199
  3. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 97
  4. 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistencycited by 97
  5. 2023Backdoor Defense via Adaptively Splitting Poisoned Datasetcited by 43
  6. 2024IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistencycited by 39
  7. 2022Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanescited by 32
  8. 2023Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Soundcited by 30
  9. 2023Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypotscited by 19
  10. 2022Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computingcited by 6
  11. 2024The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Datacited by 4
  12. 2024Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Datacited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Protecting against simultaneous data poisoning attacks
  2. 2026Low-ASR Backdoors: Exploiting Attack Success Rate Reduction and Attacker-Defender Asymmetry ↗
  3. 2026IU: Imperceptible Universal Backdoor Attack
  4. 2025Backdoor Attacks and Defenses in Computer Vision Domain: A Survey
  5. 2022Few-shot Backdoor Attacks via Neural Tangent Kernels
  6. 2021Backdoor Attacks on Self-Supervised Learning
  7. 2021Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
  8. 2026DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning ↗