SemPurify: Semantics-Aware Data Purification for Black-Box Backdoor Defense

Backdoor attacks have emerged as a critical security threat in machine learning, where adversaries embed triggers within poisoned training samples to manipulate a model's predictions on targeted inputs while leaving its general behavior unaffected. This stealthy nature makes backdoor attacks...

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models

Multimodal Diffusion Language Models MDLMs have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that well-established data-poisoning pipelines can successfully implant...

LogPurge: Log Data Purification for Anomaly Detection Via Rule-Enhanced Filtering

Log anomaly detection, which is critical for identifying system failures and preempting security breaches, detects irregular patterns within large volumes of log data, and impacts domains such as service reliability, performance optimization, and database log analysis. Modern log anomaly detectio...