Double-Blind Cleanser: Blindly Unlearning Backdoors Without Clean Data
Summary
Backdoor attacks compromise AI models by injecting hidden triggers into training data that cause the model to misclassify inputs containing those triggers. This paper introduces Double-Blind Cleanser (DBC), a method that removes backdoors without needing access to clean data or knowing what the triggers look like, using two techniques: catastrophic forgetting (making the model forget the backdoor behavior) and Sharpness-Aware Minimization (SAM, which smooths the model's decision boundaries to restore normal functionality).
Solution / Mitigation
The paper describes DBC's approach: "It first leverages catastrophic forgetting to eliminate the backdoor behavior. It then applies Sharpness-Aware Minimization (SAM) to flatten the loss landscape, improving generalization and restoring legitimate functionality without requiring prior knowledge of triggers or poisoned samples. To further enhance the flatness of the loss landscape, DBC employs an importance sampling strategy that prioritizes samples most sensitive to weight perturbations, effectively reducing the impact of poisoned instances."
Classification
Related Issues
Original source: http://ieeexplore.ieee.org/document/11570205
First tracked: July 6, 2026 at 08:03 PM
Classified by LLM (prompt v3) · confidence: 92%