Evaluating LLM-generated malware: an end-to-end framework and measurement study

SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs

This work presents SCRIPTIOC-BENCH, a benchmark for measuring static IOC extraction capability on real-world malicious scripts, and evaluates a broad range of proprietary and open-weight LLMs, showing that IOC recovery without execution remains challenging across model scales.

Security Analysis of LLM-Generated Web API Backends

A security assessment on 75 FastAPI backends generated by three contemporary LLMs revealed a disconnect between functional correctness and secure logic, which is interpreted as a review-risk pattern, which is called the human-in-the-loop paradox.

LLM-Powered Automated Attacks

The increasing integration of large language models (LLMs) into systems introduces new attack surfaces that extend beyond traditional software vulnerabilities. While LLMs are commonly protected by prompt-level security mechanisms, recent researches show that these controls can be bypassed through carefully crafted inpu...

Base Semantics—A Novel Approach for Minimizing Malware Detection Rules

The rapid evolution of malware variants has increasingly undermined traditional signature‐based detection techniques, which are easily evaded through obfuscation and polymorphism that preserve malicious functionality. This challenge is particularly acute in Internet of Things (IoT) environments, where device heteroge...

Bolstering Binary Datasets for Malware Detection Through Programmatic Data Augmentation

Are Tigress-Obfuscated Binaries Representative of Real Linux Malware? A Static Feature Measurement Study

Malware corpora produced through source code obfuscation tools like Tigress are commonly employed for malware detection and binary analysis purposes; however, the representative nature of such malware corpora in relation to real-life Linux malware is far from sufficiently validated. This research work investigates whet...