相关论文: ICON: Indirect Prompt Injection Defense for Agents…

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…

A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the…

The protection of cyber Intellectual Property (IP) such as web content is an increasingly critical concern. The rise of large language models (LLMs) with online retrieval capabilities enables convenient access to information but often…

Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inference, which outsources the early-layer inference to ensure…

Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over…

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

Signature-based Intrusion Detection Systems (IDS) detect malicious activities by matching network or host activity against predefined rules. These rules are derived from extensive Cyber Threat Intelligence (CTI), which includes attack…

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed…

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to…

Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Prompt injection constitutes a significant challenge for generative AI systems by inducing unintended outputs. We introduce a multi-agent NLP framework specifically designed to address prompt injection vulnerabilities through layered…

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…

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…

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

This work demonstrates that LLM-based web navigation agents offer powerful automation capabilities but are vulnerable to Indirect Prompt Injection (IPI) attacks. We show that adversaries can embed universal adversarial triggers in webpage…

Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, making it increasingly challenging for traditional threat…