相关论文: Here Comes The AI Worm: Unleashing Zero-click Worm…

In this paper, we show that with the ability to jailbreak a GenAI model, attackers can escalate the outcome of attacks against RAG-based GenAI-powered applications in severity and scale. In the first part of the paper, we show that…

In this paper we argue that a jailbroken GenAI model can cause substantial harm to GenAI-powered applications and facilitate PromptWare, a new type of attack that flips the GenAI model's behavior from serving an application to attacking it.…

Encounter-based network is a frequently-disconnected wireless ad-hoc network requiring immediate neighbors to store and forward aggregated data for information disseminations. Using traditional approaches such as gateways or firewalls for…

The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI…

Self-propagating malware (e.g., an Internet worm) exploits security loopholes in software to infect servers and then use them to scan the Internet for more vulnerable servers. While the mechanisms of worm infection and their propagation…

We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting (XSS): malicious text is hidden within seemingly trusted content,…

Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…

The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim…

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

Since the first Graphical User Interface (GUI) prototype was invented in the 1970s, GUI systems have been deployed into various personal computer systems and server platforms. Recently, with the development of artificial intelligence (AI)…

The rise of text-to-image (T2I) models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial…

This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…

As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

This report presents a real-world case study demonstrating how prompt injection can attack large language model platforms such as ChatGPT according to a proposed injection framework. By providing three real-world examples, we show how…

Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant knowledge sources. It is particularly useful in chatbot…

An encounter-based network is a frequently disconnected wireless ad-hoc network requiring nearby neighbors to store and forward data utilizing mobility and encounters over time. Using traditional approaches such as gateways or firewalls for…

Malware detectors based on machine learning are vulnerable to adversarial attacks. Generative Adversarial Networks (GAN) are architectures based on Neural Networks that could produce successful adversarial samples. The interest towards this…

Recent research has shown that large language models (LLMs) are particularly vulnerable to adversarial attacks. Since the release of ChatGPT, various industries are adopting LLM-based chatbots and virtual assistants in their data workflows.…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…