mlsanityData to 14 Oct 2026

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning

arXiv 2502.11687 ↗First posted 17 Feb 2025cs.CR cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade detection by maintaining a low pre-deployment attack success rate (ASR) and restoring high ASR post-deployment via machine unlearning. Existing concealed backdoors are often constrained by requiring white-box or black-box access or auxiliary data, limiting their practicality when such access or data is unavailable. This paper introduces ReVeil, a concealed backdoor attack targeting the data collection phase of the DNN training pipeline, requiring no model access or auxiliary data. ReVeil maintains low pre-deployment ASR across four datasets and four trigger patterns, successfully evades three popular backdoor detection methods, and restores high ASR post-deployment through machine unlearning.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

22 of 42 references.

References · 22

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2019Machine Unlearningcited by 1,061
  3. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 459
  4. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  5. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  6. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  7. 2020Amnesiac Machine Learningcited by 319
  8. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  9. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  10. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 242
  11. 2020Blind Backdoors in Deep Learning Modelscited by 182
  12. 2021Adaptive Machine Unlearningcited by 176
10 more
  1. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  2. 2022BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learningcited by 86
  3. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  4. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 63
  5. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
  6. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 43
  7. 2023Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examplescited by 43
  8. 2023Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Featurescited by 37
  9. 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
  10. 2022PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Erased but Not Forgotten: How Backdoors Compromise Concept Erasurecited by 9
  2. 2026Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Modelscited by 0
  3. 2026InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Resetcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
  2. 2026Low-ASR Backdoors: Exploiting Attack Success Rate Reduction and Attacker-Defender Asymmetry ↗
  3. 2024Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
  4. 2025DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
  5. 2022Backdoor Defense via Suppressing Model Shortcuts
  6. 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
  7. 2023Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
  8. 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming