Automating Host Exploitation with AI
A simple, low-interaction SSH honeypot server in Python for easy network traffic monitoring
A simple, low-interaction LDAP honeypot server in Python for easy network traffic monitoring
A simple, low-interaction DNS honeypot server in Python for easy network traffic monitoring
A simple, low-interaction NTP honeypot server in Python for easy network traffic monitoring
Multilingual Deception Detection of GPT-generated Hotel Reviews
Deception Detection with Machine Learning: a literature review and statistical analisys
A simple, low-interaction SIP honeypot server in Python for easy network traffic monitoring
A simple, low-interaction TELNET honeypot server in Python for easy network traffic monitoring
A simple, low-interaction FTP honeypot server in Python for easy network traffic monitoring
A simple, low-interaction PostgreSQL honeypot server in Python for easy network traffic monitoring
Repository for the paper "Can lies be faked? Comparing low-stakes and high-stakes deception video datasets from a Machine Learning perspective"
An official repository for the "Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs" paper.
Classification for Deception Detection on Amazon Reviews Dataset
IFRIT is an AI-powered reverse proxy that intercepts incoming requests in real time, classifying each one as legitimate or malicious. Legitimate traffic is forwarded to backend; malicious traffic receives a customized AI-generated honeypot response that mimics the requested resource with fabricated data, deceiving attackers into wasting time on it.
A repository containing the demostrative code of the implementation of the 9 RNN architectures for our research.
Multi-agent strategic deception evaluation framework for LLMs using Secret Hitler as a testbed. Analyzes AI reasoning, trust dynamics, and deceptive behavior patterns.
Investigating whether language models encode anticipated social consequences in their activations. Uses a 2x2 factorial design crossing truth × social valence to show that models are more sensitive to expected approval/disapproval than to truth itself.
A simple, low-interaction HTTPS honeypot server in Python for easy network traffic monitoring
Add a description, image, and links to the deception-detection topic page so that developers can more easily learn about it.
To associate your repository with the deception-detection topic, visit your repo's landing page and select "manage topics."