Sentinel-GPT

Sentinel-GPT: IA Agéntica para la Caza de Amenazas 🛡️ Un pipeline automatizado de ciberseguridad que transforma registros sin procesar de Azure en inteligencia accionable mediante razonamiento basado en LLM. 📖 Descripción general Sentinel-GPT es un Agente de IA especializado en la caza de amenazas...

BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense

Cyber attacks are increasingly automated, narrowing the time available for human analysts to detect, reason about, and respond to intrusions. Large language models LLMs offer a promising foundation for autonomous cyber defense because they can correlate heterogeneous evidence and reason about...

Stealing AI Reasoning Traces

Interesting research: "Stealing Reasoning Traces from Proprietary LLM APIs": Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces...

Towards LLM-Enhanced Android Taint Analysis

Taint analysis is a fundamental technique for detecting sensitive data leaks in Android apps. However, traditional static tools, such as FlowDroid, still face well-known challenges due to the complexity of accurately modeling the Android framework. In this paper, we investigate whether...

Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making

Large language models LLMs are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived...

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the...

BoxPwnr v0.4.0

BoxPwnr A fun experiment to see how far Large Language Models LLMs can go in solving CTF challenges and security labs on their own. It started with HackTheBox and now covers many platforms and agentic solvers. BoxPwnr provides a plug and play system that can be used to test performance of differe...