相关论文: Image-based Prompt Injection: Hijacking Multimodal…

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language…

Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extensive knowledge embedded in LLMs, these applications can…

Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image…

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output text, OS agents autonomously perform computer-based tasks in…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

A popular method to adapt large language models (LLMs) to new tasks is in-context learning (ICL), which is effective but incurs high inference costs as context length grows. In this paper we propose a method to perform instruction…

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…

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our…

Machine learning based intrusion detection systems are increasingly targeted by black box adversarial attacks, where attackers craft evasive inputs using indirect feedback such as binary outputs or behavioral signals like response time and…

LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…