TF-MAL-elf.drifter

Description

ThreatFox malware family `elf.drifter`. Printable name: Drifter. Aliases: Dongfeng.

Indicators of Compromise (0)

No indicators of compromise on this threat.

References (1)

• ThreatFox: IOCs for this family ThreatFox Malwares

• Addressing malware family concept drift with triplet autoencoder
  web:arxiv.org

  Machine learning is increasingly vital in cybersecurity, especially in malware detection. However, concept drift, where the characteristics of malware change over time, poses a challenge for maintaining the efficacy of these detection systems. Concept drift can occur in two forms: the emergence of entirely new malware families and the evolution of existing ones. This paper proposes an ...

  2026-09-25 21:25 UTC
• Addressing malware family concept drift with triplet autoencoder
  web:arxiv.org

  This paper presents an approach to addressing concept drift in malware family detection, specifically focusing on the emergence of new malware families. Our method effectively differentiates between known and new malware families by leveraging a triplet autoencoder and the DBSCAN clustering algorithm.

  2026-09-25 21:25 UTC
• PDF Navigating Concept Drift and Packing Complexity in Malware Family ...
  web:ceur-ws.org

  This paper is organized as follows: Section 2 reviews relevant research on malware detection, malware family classification and concept drift. Section 3 describes our methodology, including data processing and model design.

  2026-09-25 21:25 UTC
• Tracking concept drift in malware families - ACM Digital Library
  web:dl.acm.org

  Index Terms Tracking concept drift in malware families Security and privacy Intrusion/anomaly detection and malware mitigation Social and professional topics Computing / technology policy Computer crime

  2026-09-25 21:25 UTC
• PDF Drift Forensics of Malware Classifiers - Fabio Pierazzi
  web:fabio.pierazzi.com

  How and why does concept drift impact the performance of Artificial Intelligence (AI) classifiers in detecting and classifying multi- family Android malware over time? In this paper, we contribute to the field of Drift Forensics, a newly established direction of post-hoc analysis of drifted data [17, 38, 48, 50].

  2026-09-25 21:25 UTC
• One step forward, two steps back: ML-based malware detection under ...
  web:link.springer.com

  The malware revival chains reflect a series in which malicious actors revived and reused malware . We notice that, in some cases, the revived malware are labeled as a different malicious family by the malware detection engines.

  2026-09-25 21:25 UTC
• Towards Explainable Drift Detection and Early Retrain in ML-Based ...
  web:link.springer.com

  The current largest challenge in ML-based malware detection is maintaining high detection rates while samples evolve. Although multiple works have proposed drift detectors and retraining-aware pipelines that work with reasonable efficiency, none of these detectors...

  2026-09-25 21:25 UTC
• PDF Towards Explainable Drift Detection and Early Retrain in ML-based ...
  web:marcusbotacin.github.io

  Even if a drift detector points out that an in-the-wild stream of malware has changed its distribution, analysts cannot know what is present in the new samples that was not present in the previous ones, which limits remediation and prevention actions.

  2026-09-25 21:25 UTC
• FL-MalDrift: a federated learning framework for malware ... - Nature
  web:www.nature.com

  These results provide strong statistical evidence that local drift detection and mitigation substantially enhance global model performance in federated malware detection scenarios.

  2026-09-25 21:25 UTC
• BenchMFC: A benchmark dataset for trustworthy malware family ...
  web:www.sciencedirect.com

  BenchMFC provides clear family , packer, and timestamp tags for each sample, it thus can support research on three types of malware concept drift: 1) unseen families, 2) packed families, and 3) evolved families.

  2026-09-25 21:25 UTC

Only Available for Registered Users. Sign in to view.