Related papers: MUZZLE: Adaptive Agentic Red-Teaming of Web Agents…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling.…

Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a…

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency…

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

LLM-integrated applications are vulnerable to prompt injection attacks, where an attacker contaminates the input to inject malicious instructions, causing the LLM to follow the attacker's intent instead of the original user's. Existing…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, and generating exploits for potential vulnerabilities. This…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Reinforcement learning agents are susceptible to evasion attacks during deployment. In single-agent environments, these attacks can occur through imperceptible perturbations injected into the inputs of the victim policy network. In…

Industrial control systems (ICS) are vital to modern infrastructure but increasingly vulnerable to cybersecurity threats, particularly through weaknesses in their communication protocols. This paper presents MALF (Multi-Agent LLM Fuzzing…

Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every…

Inference attacks have been widely studied and offer a systematic risk assessment of ML services; however, their implementation and the attack parameters for optimal estimation are challenging for non-experts. The emergence of advanced…

Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are…