中文
相关论文

相关论文: Exfiltration of personal information from ChatGPT …

200 篇论文

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to cater to specific needs has opened new frontiers in AI…

密码学与安全 · 计算机科学 2024-05-28 Jiahao Yu , Yuhang Wu , Dong Shu , Mingyu Jin , Sabrina Yang , Xinyu Xing

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…

密码学与安全 · 计算机科学 2025-04-24 Xiangyu Chang , Guang Dai , Hao Di , Haishan Ye

LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples…

计算与语言 · 计算机科学 2023-05-25 Aman Priyanshu , Supriti Vijay , Ayush Kumar , Rakshit Naidu , Fatemehsadat Mireshghallah

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…

密码学与安全 · 计算机科学 2026-05-19 Hongjang Yang , Hyunsik Na , Daeseon Choi

As artificial intelligence technology continues to advance, chatbots are becoming increasingly powerful. Among them, ChatGPT, launched by OpenAI, has garnered widespread attention globally due to its powerful natural language processing…

密码学与安全 · 计算机科学 2026-02-03 Yushan Xiang , Zhongwen Li , Xiaoqi Li

Large language models and AI chatbots have been at the forefront of democratizing artificial intelligence. However, the releases of ChatGPT and other similar tools have been followed by growing concerns regarding the difficulty of…

密码学与安全 · 计算机科学 2024-02-05 Sippo Rossi , Alisia Marianne Michel , Raghava Rao Mukkamala , Jason Bennett Thatcher

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

密码学与安全 · 计算机科学 2023-05-08 Kai Greshake , Sahar Abdelnabi , Shailesh Mishra , Christoph Endres , Thorsten Holz , Mario Fritz

With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) like GPT…

软件工程 · 计算机科学 2024-04-15 Chenyuan Zhang , Hao Liu , Jiutian Zeng , Kejing Yang , Yuhong Li , Hui Li

ChatGPT is currently the most popular large language model (LLM), with over 100 million users, making a significant impact on people's lives. However, due to the presence of jailbreak vulnerabilities, ChatGPT might have negative effects on…

软件工程 · 计算机科学 2023-12-19 Poorna Chander Reddy Puttaparthi , Soham Sanjay Deo , Hakan Gul , Yiming Tang , Weiyi Shang , Zhe Yu

Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are…

密码学与安全 · 计算机科学 2025-11-11 Yigitcan Kaya , Anton Landerer , Stijn Pletinckx , Michelle Zimmermann , Christopher Kruegel , Giovanni Vigna

ChatGPT is a generative pretrained transformer language model created using artificial intelligence implemented as chatbot which can provide very detailed responses to a wide variety of questions. As a very contemporary phenomenon, this…

密码学与安全 · 计算机科学 2023-07-14 Sheetal Temara

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

计算与语言 · 计算机科学 2026-04-14 Hwan Chang , Yonghyun Jun , Hwanhee Lee

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approaches that aim to detect…

密码学与安全 · 计算机科学 2025-04-01 Shih-Han Chan

The rapid advancements in generative AI models, such as ChatGPT, have introduced both significant benefits and new risks within the cybersecurity landscape. This paper investigates the potential misuse of the latest AI model, ChatGPT-4o…

密码学与安全 · 计算机科学 2025-03-04 Rina Mishra , Gaurav Varshney , Shreya Singh

Large language models (LLMs) demonstrate powerful information handling capabilities and are widely integrated into chatbot applications. OpenAI provides a platform for developers to construct custom GPTs, extending ChatGPT's functions and…

密码学与安全 · 计算机科学 2025-06-05 Wei Wenying , Zhao Kaifa , Xue Lei , Fan Ming

The ability of ChatGPT to generate human-like responses and understand context has made it a popular tool for conversational agents, content creation, data analysis, and research and innovation. However, its effectiveness and ease of…

密码学与安全 · 计算机科学 2023-05-10 Sayak Saha Roy , Krishna Vamsi Naragam , Shirin Nilizadeh

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

密码学与安全 · 计算机科学 2023-10-19 Yixin Wu , Rui Wen , Michael Backes , Pascal Berrang , Mathias Humbert , Yun Shen , Yang Zhang

With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from…

计算与语言 · 计算机科学 2023-11-02 Haoran Li , Dadi Guo , Wei Fan , Mingshi Xu , Jie Huang , Fanpu Meng , Yangqiu Song

Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL) fine-tuning, a new paradigm that allows language models to…

密码学与安全 · 计算机科学 2023-04-25 Jiawen Shi , Yixin Liu , Pan Zhou , Lichao Sun

This work explores injection attacks against password managers. In this setting, the adversary (only) controls their own application client, which they use to "inject" chosen payloads to a victim's client via, for example, sharing…

密码学与安全 · 计算机科学 2024-08-14 Andrés Fábrega , Armin Namavari , Rachit Agarwal , Ben Nassi , Thomas Ristenpart
‹ 上一页 1 2 3 10 下一页 ›