Related papers: Honeypot Protocol
Honeypots are designed to trap the attacker with the purpose of investigating its malicious behavior. Owing to the increasing variety and sophistication of cyber attacks, how to capture high-quality attack data has become a challenge in the…
Artificial Intelligence (AI) is playing a vital role in all aspects of technology including cyber security. Application of Conversational AI like the chatbots are also becoming very popular in the medical field to provide timely and…
Cyber-secure networked control is modeled, analyzed, and experimentally illustrated in this paper. An attack space defined by the adversary's system knowledge, disclosure, and disruption resources is introduced. Adversaries constrained by…
Internet security is getting less secure because of the existing of botnet threats. An attack plan can only be planned out to take down the botnet after the monitoring activities to understand the behaviour of a botnet. Nowadays, the…
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assurances on the system's risk established beforehand. Common…
LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if they were…
Deception plays a critical role in the financial industry, online markets, national defense, and countless other areas. Understanding and harnessing deception - especially in cyberspace - is both crucial and difficult. Recent work in this…
Traditional reactive approach of blacklisting botnets fails to adapt to the rapidly evolving landscape of cyberattacks. An automated and proactive approach to detect and block botnet hosts will immensely benefit the industry. Behavioral…
Monitoring the status of large computing systems is essential to identify unexpected behavior and improve their performance and uptime. However, due to the large-scale and distributed design of such computing systems as well as a large…
Honeypots are more and more used to collect data on malicious activities on the Internet and to better understand the strategies and techniques used by attackers to compromise target systems. Analysis and modeling methodologies are needed…
The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces…
Large language models (LLMs) are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive…
With the rapid growth of Internet of Things (IoT) devices, it is imperative to proactively understand the real-world cybersecurity threats posed to them. This paper describes our initial efforts towards building a honeypot ecosystem as a…
SQL injection remains a major threat to web applications, as existing defenses often fail against obfuscation and evolving attacks because of neglecting the request-response context. This paper presents a context-enriched SQL injection…
The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…
As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model…
The Model Context Protocol (MCP) is an emerging open standard that defines a unified, bi-directional communication and dynamic discovery protocol between AI models and external tools or resources, aiming to enhance interoperability and…
Trustworthy evaluations of dangerous capabilities are increasingly crucial for determining whether an AI system is safe to deploy. One empirically demonstrated threat is sandbagging - the strategic underperformance on evaluations by AI…
The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find very few works and no consensus…
Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including…