5 papers · 1 filter
Improving LLM-Based SSH Honeypots Through Prompting and Fine-Tuning
Muris Sladić, Veronica Valeros, Eman Alibalić +1
LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These include no stable versioning, provide…
Ghost Without Shell: Measuring Non-Interactive SSH Attacks on Honeypots
Veronica Valeros, Muris SladiÄ, Sebastian Garcia
Cyber deception research has focused on improving honeypot deception capabilities to increase attacker engagement and extend their interactions to collect more and better intellige…
AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deception
Muris SladiÄ, Eman AlibaliÄ, Veronica Valeros +2
LLM-based SSH honeypots can generate believable interactions, but evaluations indicate they remain somewhat identifiable to determined attackers, indicating the need for a better s…
VelLMes: A high-interaction AI-based deception framework
Muris SladiÄ, Veronica Valeros, Carlos Catania +1
There are very few SotA deception systems based on Large Language Models. The existing ones are limited only to simulating one type of service, mainly SSH shells. These systems - b…
LLM in the Shell: Generative Honeypots
Muris SladiÄ, Veronica Valeros, Carlos Catania +1
Honeypots are essential tools in cybersecurity for early detection, threat intelligence gathering, and analysis of attacker's behavior. However, most of them lack the required real…