ArXiv▲ 43

Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition

ArXiv|Monday, August 24, 2026|6 days ago|Kyle Stein

No AI summary available for this article.

Why It Matters

The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch.

Provenance

Discovered via ArXiv and published by ArXiv.

Open original ↗Source profile →

Key Claims

However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten.
While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FSCIL), where new malware classes must be learned from only a small number of labeled examples, remains comparatively underexplored.
Therefore, this work investigates the FSCIL setti...

Original description

The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FSCIL), where new malware classes must be learned from only a small number of labeled examples, remains comparatively underexplored. Therefore, this work investigates the FSCIL setti...

arxiv cs.CR cs.AI publisher:arxiv tier:research

Read on ArXiv ↗← Back to feed

Discovered via ArXiv

Research papers and preprints from arXiv.

Publisher: arxiv.org

ID: http://arxiv.org/abs/2608.23536v1 · Indexed 6 days ago