HashRuler: Lightweight Detection of Anomalous Hash Codes for Backdoor Defense

Deep hashing models, which compress images into compact codes for fast retrieval, can be poisoned by backdoor attacks (hidden malicious behavior triggered by specific inputs) that manipulate their hash codes while appearing benign. Researchers developed HashRuler, a lightweight detection system that identifies these compromised samples by measuring two types of anomalies in the hash codes: how far a sample deviates from its class's typical hash center, and how it behaves as an outlier compared to nearby samples.