The paper evaluates seven open‑source small language models (20 M–1.5 B parameters) on two post‑exploitation code‑generation tasks—Directory Enumeration and Backdoor Generation—in both Python and Lua. It finds that offensive code‑generation performance does not scale linearly with model size; instead, task formulation and prompting strategy play a larger role. Using algorithmic formulation and few‑shot prompting, Qwen2.5‑Coder 1.5B achieves near‑perfect success rates on both tasks in Python and high success in Lua.
arXiv:2607. 20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours.
arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.
arXiv:2604. 27143v2 Announce Type: replace-cross Abstract: Cloud-based Large Language Models (LLMs) can perform autonomous penetration-testing sub-tasks such as Linux privilege escalation, but raise security, privacy, and sovereignty concerns.
arXiv:2607. 20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools.
arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv:2606. 16244v1 Announce Type: cross Abstract: Large language models routinely generate code with exploitable security flaws.
SCRIPTIOC-BENCH is a benchmark designed to evaluate how well large language models can statically extract indicators of compromise (IOCs) from script-based malware. It contains 634 manually verified JavaScript, PowerShell, and VBScript samples and covers four IOC types—URLs, domains, IP addresses, and filesystem artifacts—while distinguishing between directly exposed and encoded indicators. Experiments show that even the best models achieve only 65.4 F1, and a false‑positive taxonomy is introduced to analyze error patterns, with two mitigations (deterministic string utilities and task‑specific adaptation) improving precision and shifting errors toward sample‑grounded mismatches.
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resource...
arXiv:2601. 21233v2 Announce Type: replace Abstract: Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction.
The paper introduces the Static‑Pass Dynamic‑Fail (SPDF) phenomenon, showing that static analysis can miss vulnerabilities that are exploitable at runtime. Using a three‑stage pipeline—static scanning, LLM‑driven CWE reasoning, and autonomous exploit verification—it evaluated 1,355 Python samples and found that 14.53% of samples that passed static checks were actually exploitable. The study highlights that static‑analysis success and runtime security are distinct assurance layers, especially for AI‑generated and security‑sensitive code.