Related papers: ShieldNet: Network-Level Guardrails against Emergi…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Model Context Protocol (MCP) is a rapidly adopted standard for defining and invoking external tools in LLM applications. The multi-layered architecture of MCP introduces new attack surfaces such as tool poisoning, in addition to traditional…

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining (STAC), a novel…

Agent skills are increasingly used to extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources. While improving reusability, this modular design also introduces a new supply-chain attack surface: a…

Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe…

Cross-chain bridges play a vital role in enabling blockchain interoperability. However, due to the inherent design flaws and the enormous value they hold, they have become prime targets for hacker attacks. Existing detection methods show…

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trust tools exposed by potentially untrusted MCP servers.…

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a…

Retrieval-Augmented Generation (RAG) has significantly enhanced the factual accuracy and domain adaptability of Large Language Models (LLMs). This advancement has enabled their widespread deployment across sensitive domains such as…

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

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…

Detecting prompt injection and jailbreak attacks is critical for deploying LLM-based agents safely. As agents increasingly process untrusted data from emails, documents, tool outputs, and external APIs, robust attack detection becomes…

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

The electric vehicle (EV) battery supply chain's vulnerability to disruptions necessitates advanced predictive analytics. We present SHIELD (Schema-based Hierarchical Induction for EV supply chain Disruption), a system integrating Large…

The Model Context Protocol (MCP) has emerged as a standardized interface enabling seamless integration between Large Language Models (LLMs) and external data sources and tools. While MCP significantly reduces development complexity and…