相关论文: Web Fraud Attacks Against LLM-Driven Multi-Agent S…

Modern overlay security mechanisms like Web Application Firewalls (WAF) suffer from inability to recognize custom high-level application logic and data objects, which results in low accuracy, high false positives rates, and overhelming…

With the rapid development of LLM-based multi-agent systems (MAS), their significant safety and security concerns have emerged, which introduce novel risks going beyond single agents or LLMs. Despite attempts to address these issues, the…

Large language model (LLM) agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored…

The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

This paper introduces a novel attack vector that leverages website cloaking techniques to compromise autonomous web-browsing agents powered by Large Language Models (LLMs). As these agents become more prevalent, their unique and often…

Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by…

Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally crafted instances,…

Automated evidence-based misinformation detection systems, which evaluate the veracity of short claims against evidence, lack comprehensive analysis of their adversarial vulnerabilities. Existing black-box text-based adversarial attacks are…

This paper formalises the literature on emerging design patterns and paradigms for Large Language Model (LLM)-enabled multi-agent systems (MAS), evaluating their practical utility across various domains. We define key architectural…

The web is experiencing an explosive growth in the last years. New technologies are introduced at a very fast-pace with the aim of narrowing the gap between web-based applications and traditional desktop applications. The results are web…

Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual feasibility of the…

With increasingly sophisticated large language models (LLMs), the potential for abuse rises drastically. As a submission to the Swiss AI Safety Prize, we present a novel type of metamorphic malware leveraging LLMs for two key processes.…

Multi-Agent Systems (MAS) excel at accomplishing complex objectives through the collaborative efforts of individual agents. Among the methodologies employed in MAS, Multi-Agent Reinforcement Learning (MARL) stands out as one of the most…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence,…

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…