中文
相关论文

相关论文: Overcoming the Retrieval Barrier: Indirect Prompt …

200 篇论文

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…

计算与语言 · 计算机科学 2026-04-07 Wenhui Zhu , Xuanzhao Dong , Xiwen Chen , Rui Cai , Peijie Qiu , Zhipeng Wang , Oana Frunza , Shao Tang , Jindong Gu , Yalin Wang

Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a…

密码学与安全 · 计算机科学 2025-05-23 Junjie Xiong , Changjia Zhu , Shuhang Lin , Chong Zhang , Yongfeng Zhang , Yao Liu , Lingyao Li

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

密码学与安全 · 计算机科学 2026-05-18 Jiate Li , Defu Cao , Li Li , Wei Yang , Yuehan Qin , Chenxiao Yu , Tiannuo Yang , Ryan A. Rossi , Yan Liu , Xiyang Hu , Yue Zhao

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

人工智能 · 计算机科学 2025-09-10 Minghui Li , Hao Zhang , Yechao Zhang , Wei Wan , Shengshan Hu , pei Xiaobing , Jing Wang

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…

密码学与安全 · 计算机科学 2025-05-05 Wenjie Qu , Yuguang Zhou , Yongji Wu , Tingsong Xiao , Binhang Yuan , Yiming Li , Jiaheng Zhang

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models (LLMs) to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are…

密码学与安全 · 计算机科学 2026-02-06 Takashi Koide , Hiroki Nakano , Daiki Chiba

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…

密码学与安全 · 计算机科学 2025-10-07 Yulin Chen , Haoran Li , Yuexin Li , Yue Liu , Yangqiu Song , Bryan Hooi

Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical environments. While LVLMs are known to be vulnerable to prompt injection attacks, existing…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Chen Ling , Kai Hu , Hangcheng Liu , Xingshuo Han , Tianwei Zhang , Changhai Ou

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…

密码学与安全 · 计算机科学 2026-03-12 Yu He , Haozhe Zhu , Yiming Li , Shuo Shao , Hongwei Yao , Zhihao Liu , Zhan Qin

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

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…

机器学习 · 计算机科学 2025-05-30 Xiangyu Zhou , Yao Qiang , Saleh Zare Zade , Prashant Khanduri , Dongxiao Zhu

Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions. Existing defenses…

密码学与安全 · 计算机科学 2025-06-12 Kaijie Zhu , Xianjun Yang , Jindong Wang , Wenbo Guo , William Yang Wang

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…

计算机视觉与模式识别 · 计算机科学 2025-09-19 Saket S. Chaturvedi , Gaurav Bagwe , Lan Zhang , Xiaoyong Yuan

Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…

密码学与安全 · 计算机科学 2024-03-25 Keegan Hines , Gary Lopez , Matthew Hall , Federico Zarfati , Yonatan Zunger , Emre Kiciman

Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existing defenses typically rely on strict filtering or refusal…

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…

密码学与安全 · 计算机科学 2025-08-22 Hengyu An , Jinghuai Zhang , Tianyu Du , Chunyi Zhou , Qingming Li , Tao Lin , Shouling Ji

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…

密码学与安全 · 计算机科学 2026-01-27 Wei Zou , Yupei Liu , Yanting Wang , Ying Chen , Neil Gong , Jinyuan Jia

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…

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

密码学与安全 · 计算机科学 2025-09-17 Mengxiao Wang , Yuxuan Zhang , Guofei Gu

Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential…

密码学与安全 · 计算机科学 2024-11-06 Emet Bethany , Mazal Bethany , Juan Arturo Nolazco Flores , Sumit Kumar Jha , Peyman Najafirad