中文
相关论文

相关论文: The Man Behind the Sound: Demystifying Audio Priva…

200 篇论文

Due to the correlational structure in our traits such as identities, cultures, and political attitudes, seemingly innocuous preferences like following a band or using a specific slang can reveal private traits. This possibility, especially…

社会与信息网络 · 计算机科学 2026-03-16 Byunghwee Lee , Sangyeon Kim , Filippo Menczer , Yong-Yeol Ahn , Haewoon Kwak , Jisun An

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

密码学与安全 · 计算机科学 2026-04-21 Zheng Hui , Yijiang River Dong , Sanhanat Sivapiromrat , Ehsan Shareghi , Nigel Collier

Large language models (LLMs) are increasingly used in sensitive domains, where their ability to infer personal data from seemingly benign text introduces emerging privacy risks. While recent LLM-based anonymization methods help mitigate…

计算与语言 · 计算机科学 2025-10-27 Kyuyoung Kim , Hyunjun Jeon , Jinwoo Shin

Theory of Mind (ToM) in Large Language Models (LLMs) refers to the model's ability to infer the mental states of others, with failures in this ability often manifesting as systemic implicit biases. Assessing this challenge is difficult, as…

计算与语言 · 计算机科学 2026-01-19 Yanlin Li , Hao Liu , Huimin Liu , Kun Wang , Yinwei Wei , Yupeng Hu

With the rapid advancement of Large Language Models (LLMs), LLM-based agents exhibit exceptional abilities in understanding and generating natural language, enabling human-like collaboration and information transmission in LLM-based…

人工智能 · 计算机科学 2025-10-07 Hailong Yang , Renhuo Zhao , Guanjin Wang , Zhaohong Deng

As large language models (LLMs) become integral to recruitment processes, concerns about AI-induced bias have intensified. This study examines biases in candidate interview reports generated by Claude 3.5 Sonnet, GPT-4o, Gemini 1.5, and…

人工智能 · 计算机科学 2024-10-23 Django Beatty , Kritsada Masanthia , Teepakorn Kaphol , Niphan Sethi

Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous…

计算与语言 · 计算机科学 2026-03-17 Scott Merrill , Shashank Srivastava

Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle…

计算与语言 · 计算机科学 2026-03-17 Shaowei Guan , Yu Zhai , Hin Chi Kwok , Jiawei Du , Xinyu Feng , Jing Li , Harry Qin , Vivian Hui

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

密码学与安全 · 计算机科学 2025-12-17 Yihan Liao , Jacky Keung , Xiaoxue Ma , Jingyu Zhang , Yicheng Sun

Large Language Models (LLMs) are increasingly being used for automated evaluations and explaining them. However, concerns about explanation quality, consistency, and hallucinations remain open research challenges, particularly in…

人机交互 · 计算机科学 2025-04-18 Vincent Freiberger , Arthur Fleig , Erik Buchmann

With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models…

计算与语言 · 计算机科学 2025-11-03 Jayden Serenari , Stephen Lee

Large language models (LLMs) are the foundation of the current successes of artificial intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks and encourage mitigation efforts these models need adequate…

计算与语言 · 计算机科学 2025-01-14 Carolin M. Schuster , Maria-Alexandra Dinisor , Shashwat Ghatiwala , Georg Groh

Large audio language models (LALMs) are increasingly used to reason over long audio clips, yet deployment often compresses audio before inference to reduce memory and latency. The risk is that compression can leave aggregate accuracy…

音频与语音处理 · 电气工程与系统科学 2026-05-08 Amir Ivry

Emotion recognition in speech is a challenging multimodal task that requires understanding both verbal content and vocal nuances. This paper introduces a novel approach to emotion detection using Large Language Models (LLMs), which have…

计算与语言 · 计算机科学 2024-12-24 Zehui Wu , Ziwei Gong , Lin Ai , Pengyuan Shi , Kaan Donbekci , Julia Hirschberg

Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despite the progress made, the challenge of detecting high-risk…

计算与语言 · 计算机科学 2024-06-26 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds,…

声音 · 计算机科学 2026-04-28 Chen-An Li , Tzu-Han Lin , Hung-yi Lee

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

密码学与安全 · 计算机科学 2026-04-21 Dong Yan , Jian Liang , Ran He , Tieniu Tan

Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be…

声音 · 计算机科学 2026-03-10 Neta Glazer , Lenny Aharon , Ethan Fetaya

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…

密码学与安全 · 计算机科学 2025-10-21 Sarah Egler , John Schulman , Nicholas Carlini

Large language models (LLMs) increasingly reach real-world applications, necessitating a better understanding of their behaviour. Their size and complexity complicate traditional assessment methods, causing the emergence of alternative…

人工智能 · 计算机科学 2025-05-13 Sanne Peereboom , Inga Schwabe , Bennett Kleinberg
‹ 上一页 1 8 9 10 下一页 ›