中文
相关论文

相关论文: SNEAK: Evaluating Strategic Communication and Info…

200 篇论文

Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the…

计算机视觉与模式识别 · 计算机科学 2021-12-09 Wenbo Gou , Wen Shi , Jian Lou , Lijie Huang , Pan Zhou , Ruixuan Li

As Large Language Models (LLMs) are increasingly deployed in sensitive domains, traditional data privacy measures prove inadequate for protecting information that is implicit, contextual, or inferable - what we define as semantic privacy.…

密码学与安全 · 计算机科学 2025-07-17 Baihe Ma , Yanna Jiang , Xu Wang , Guangsheng Yu , Qin Wang , Caijun Sun , Chen Li , Xuelei Qi , Ying He , Wei Ni , Ren Ping Liu

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

人工智能 · 计算机科学 2026-03-31 Faouzi El Yagoubi , Godwin Badu-Marfo , Ranwa Al Mallah

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

密码学与安全 · 计算机科学 2021-02-24 Huseyin A. Inan , Osman Ramadan , Lukas Wutschitz , Daniel Jones , Victor Rühle , James Withers , Robert Sim

Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…

密码学与安全 · 计算机科学 2025-11-06 Geoff McDonald , Jonathan Bar Or

Large language models (LLMs) have been shown to perform well at a variety of syntactic, discourse, and reasoning tasks. While LLMs are increasingly deployed in many forms including conversational agents that interact with humans, we lack a…

计算与语言 · 计算机科学 2024-04-02 Minje Choi , Jiaxin Pei , Sagar Kumar , Chang Shu , David Jurgens

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

计算与语言 · 计算机科学 2024-03-26 Masahiro Kaneko , Timothy Baldwin

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. Their potential to facilitate human coordination with many agents is a promising but largely under-explored area. Such capabilities would be helpful…

Large Language Models (LLMs) show significant potential in economic and strategic interactions, where communication via natural language is often prevalent. This raises key questions: Do LLMs behave rationally? How do they perform compared…

计算与语言 · 计算机科学 2026-03-03 Eilam Shapira , Omer Madmon , Itamar Reinman , Samuel Joseph Amouyal , Roi Reichart , Moshe Tennenholtz

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

计算与语言 · 计算机科学 2025-03-03 Shiwen Ni , Xiangtao Kong , Chengming Li , Xiping Hu , Ruifeng Xu , Jia Zhu , Min Yang

The rapid advancement of Large Language Models (LLMs) has necessitated more robust evaluation methods that go beyond static benchmarks, which are increasingly prone to data saturation and leakage. In this paper, we propose a dynamic…

计算与语言 · 计算机科学 2026-01-15 Haryo Akbarianto Wibowo , Alaa Elsetohy , Qinrong Cui , Alham Fikri Aji

Despite their wide adoption, the biases and unintended behaviors of language models remain poorly understood. In this paper, we identify and characterize a phenomenon never discussed before, which we call semantic leakage, where models leak…

计算与语言 · 计算机科学 2025-05-19 Hila Gonen , Terra Blevins , Alisa Liu , Luke Zettlemoyer , Noah A. Smith

Large Language Models (LLMs) excel at producing broadly relevant text, but this generality becomes a limitation when user-specific preferences are required, such as recommending restaurants or planning travel. In these scenarios, users…

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the…

计算与语言 · 计算机科学 2026-04-21 Hang Zeng , Xiangyu Liu , Yong Hu , Chaoyue Niu , Jiarui Zhang , Shaojie Tang , Fan Wu , Guihai Chen

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

人机交互 · 计算机科学 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Enterprise customers are increasingly adopting Large Language Models (LLMs) for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions…

Large language models (LLMs) often need to balance their internal parametric knowledge with external information, such as user beliefs and content from retrieved documents, in real-world scenarios like RAG or chat-based systems. A model's…

计算与语言 · 计算机科学 2026-04-27 Shuowei Li , Haoxin Li , Wenda Chu , Yi Fang

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…

计算与语言 · 计算机科学 2025-08-11 Hang Zeng , Xiangyu Liu , Yong Hu , Chaoyue Niu , Fan Wu , Shaojie Tang , Guihai Chen

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect…

多智能体系统 · 计算机科学 2025-11-05 Alessio Buscemi , Daniele Proverbio , Alessandro Di Stefano , The Anh Han , German Castignani , Pietro Liò
‹ 上一页 1 2 3 10 下一页 ›