arXiv AI October 19, 2026 By Gabriel Hortea, Simon Pietro Romano, Juan Tapiador, Mario Varlese

From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 23

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

arXiv:2607. 20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours.

By Adel ElZemity, Shujun Li, Budi Arief

llms agents benchmarks safety

arXiv AI

Jul 1

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.

By Seyed Bagher Hashemi Natanzi, Bo Tang

llms agents robotics safety

arXiv AI

Aug 13

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents

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.

By Benjamin Probst, Andreas Happe, J\"urgen Cito

llms rag agents benchmarks safety

arXiv AI

Jul 24

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

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.

By Ankur Singh, Jinqiu Yang, Tse-Hsun Chen

llms agents benchmarks safety

arXiv AI

Jul 21

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

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.

By Xinran Zheng, Xingzhi Qian, Yiling He, Shuo Yang, Lorenzo Cavallaro

llms agents benchmarks

Hugging Face Trending Papers

Jul 22

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

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.

llms fine-tuning efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning