中文
相关论文

相关论文: The Eye of Sherlock Holmes: Uncovering User Privat…

200 篇论文

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

人工智能 · 计算机科学 2024-11-05 Batuhan Tömekçe , Mark Vero , Robin Staab , Martin Vechev

The rapid advancement of Visual Language Models (VLMs) has enabled sophisticated analysis of visual content, leading to concerns about the inference of sensitive user attributes and subsequent privacy risks. While technical capabilities of…

人机交互 · 计算机科学 2025-08-12 Shuning Zhang , Gengrui Zhang , Yibo Meng , Ziyi Zhang , Hantao Zhao , Xin Yi , Hewu Li

Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Xiongtao Sun , Hui Li , Jiaming Zhang , Yujie Yang , Kaili Liu , Ruxin Feng , Wen Jun Tan , Wei Yang Bryan Lim

Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a…

密码学与安全 · 计算机科学 2026-04-16 Yuntao Du , Zitao Li , Bolin Ding , Yaliang Li , Hanshen Xiao , Jingren Zhou , Ninghui Li

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Simone Caldarella , Massimiliano Mancini , Elisa Ricci , Rahaf Aljundi

Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Hongyi Miao , Jun Jia , Xincheng Wang , Qianli Ma , Wei Sun , Wangqiu Zhou , Dandan Zhu , Yewen Cao , Zhi Liu , Guangtao Zhai

Our research uncovers a novel privacy risk associated with multimodal large language models (MLLMs): the ability to infer sensitive personal attributes from audio data -- a technique we term audio private attribute profiling. This…

密码学与安全 · 计算机科学 2025-08-21 Lixu Wang , Kaixiang Yao , Xinfeng Li , Dong Yang , Haoyang Li , Xiaofeng Wang , Wei Dong

As vision-language models (VLMs) become widely adopted, VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attributes from images shared on social media. This escalating…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Yucheng Fan , Jiawei Chen , Yu Tian , Zhaoxia Yin

Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, text comprehension, contextual pattern recognition, and…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Efthymios Tsaprazlis , Tiantian Feng , Anil Ramakrishna , Rahul Gupta , Shrikanth Narayanan

Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…

多媒体 · 计算机科学 2025-04-15 Junhao Xu , Jingjing Chen , Yang Jiao , Jiacheng Zhang , Zhiyu Tan , Hao Li , Yu-Gang Jiang

The proliferation of Vision-Language Models (VLMs) introduces profound privacy risks from personal videos. This paper addresses the critical yet unexplored inferential privacy threat, the risk of inferring sensitive personal attributes over…

人机交互 · 计算机科学 2025-11-05 Shuning Zhang , Zhaoxin Li , Changxi Wen , Ying Ma , Simin Li , Gengrui Zhang , Ziyi Zhang , Yibo Meng , Hantao Zhao , Xin Yi , Hewu Li

The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various utilities, unaware of the potential for privacy violations.…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Karmesh Siddharam Chaudhari , Youxiang Zhu , Amy Feng , Xiaohui Liang , Honggang Zhang

Recent years have witnessed remarkable progress in developing Vision-Language Models (VLMs) capable of processing both textual and visual inputs. These models have demonstrated impressive performance, leading to their widespread adoption in…

图像与视频处理 · 电气工程与系统科学 2025-07-15 Hanene F. Z. Brachemi Meftah , Wassim Hamidouche , Sid Ahmed Fezza , Olivier Déforges

Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been proposed for this task, training on image evaluation data to extract objective low-level…

人工智能 · 计算机科学 2026-05-15 Yoshia Abe , Tatsuya Daikoku , Yasuo Kuniyoshi

Regulatory limits on explicit targeting have not eliminated algorithmic profiling on the Web, as optimisation systems still adapt ad delivery to users' private attributes. The widespread availability of powerful zero-shot multimodal Large…

人机交互 · 计算机科学 2026-01-30 Baiyu Chen , Benjamin Tag , Hao Xue , Daniel Angus , Flora Salim

As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments becomes critical. Unlike digital chatbots, these agents operate in…

密码学与安全 · 计算机科学 2026-05-11 Junran Wang , Xinjie Shen , Zehao Jin , Pan Li

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body weight, and eye color;…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Younggun Kim , Sirnam Swetha , Fazil Kagdi , Mubarak Shah

Recent advances in multi-modal Large Language Models (M-LLMs) have demonstrated a powerful ability to synthesize implicit information from disparate sources, including images and text. These resourceful data from social media also introduce…

密码学与安全 · 计算机科学 2025-11-11 Junhao Li , Jiahao Chen , Zhou Feng , Chunyi Zhou

While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Alina Elena Baia , Alessio Xompero , Andrea Cavallaro

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

人机交互 · 计算机科学 2025-08-04 Shuning Zhang , Ying Ma , Xin Yi , Hewu Li
‹ 上一页 1 2 3 10 下一页 ›