Related papers: ARGUS: Defending LLM Agents Against Context-Aware …

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

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…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

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…

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

The emergence of LLM (Large Language Model) integrated virtual assistants has brought about a rapid transformation in communication dynamics. During virtual assistant development, some developers prefer to leverage the system message, also…

This paper introduces a novel self-consciousness defense mechanism for Large Language Models (LLMs) to combat prompt injection attacks. Unlike traditional approaches that rely on external classifiers, our method leverages the LLM's inherent…

Computer agents powered by vision-language models (VLMs) have significantly advanced human-computer interaction, enabling users to perform complex tasks through natural language instructions. However, these agents are vulnerable to context…

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like…

LLM-based agents are increasingly deployed in high-stakes scenarios such as email management, financial transactions, and code execution, where they interact with the external world through tool calling. During execution, these agents must…

Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of…

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…

The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs' advanced reasoning and role-playing capabilities to enable autonomous,…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…