相关论文: VoxPrivacy: A Benchmark for Evaluating Interaction…

Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…

Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Their profound capabilities in processing and interpreting complex language data, however,…

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…

Audio Large language models (LLMs) are increasingly deployed in the real world, where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that existing benchmarks and defences did not consider. We…

The recent progress in Vision-Language Models (VLMs) has broadened the scope of multimodal applications. However, evaluations often remain limited to functional tasks, neglecting abstract dimensions such as personality traits and human…

Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making. However, these advancements have also come with significant privacy concerns. While significant…

Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

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…

Large Audio-Language Models (LALMs) have demonstrated strong performance in audio understanding and generation. Yet, our extensive benchmarking reveals that their behavior is largely generic (e.g., summarizing spoken content) and fails to…

The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share more than necessary, increasing privacy risks via…

Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large reasoning models (MLRMs). This poses a significant privacy risk, as these widely accessible…

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted…

Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to assess speaker consistency across multi-turn dialogues remains unexplored. We present…

Conversational AI systems have emerged as key enablers of human-like interactions across diverse sectors. Nevertheless, the balance between linguistic nuance and factual accuracy has proven elusive. In this paper, we first introduce…

The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy…

The rapid development of large language models (LLMs) is redefining the landscape of human-computer interaction, and their integration into various user-service applications is becoming increasingly prevalent. However, transmitting user…

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…

Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…

Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is…