Yihan Ma

High-precision mapping of soil organic matter considering annual climate variability and multidimensional environmental factors

Xinle Zhang, Peiwen Cheng, Chao Wang, Chuan Qin et autres

Accurate mapping of soil organic matter (SOM) is critical for sustainable land management and climate change assessment. Taking Youyi Farm in Northeast China—located within one of the world's four major black soil regions—as a case study, 188 soil samples were collected and …

cn (code pays fourni par la source)

From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models

Yihan Ma, Xinyue Shen, Yiting Qu, Ning Yu et autres

Open-source Vision Language Models (VLMs) have rapidly advanced, blending natural language with visual modalities, leading them to achieve remarkable performance on tasks such as image captioning and visual question answering. However, their effectiveness in real-world scenarios remains uncertain, as real-world images—particularly hateful …

de (code pays fourni par la source)

From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models

Yihan Ma, Xinyue Shen, Yiting Qu, Ning Yu et autres

Open-source Vision Language Models (VLMs) have rapidly advanced, blending natural language with visual modalities, leading them to achieve remarkable performance on tasks such as image captioning and visual question answering. However, their effectiveness in real-world scenarios remains uncertain, as real-world images—particularly hateful …

de (code pays fourni par la source)

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models

Zeyuan Chen, Yihan Ma, Xinyue Shen, Michael Backes et autres

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership inference attack that tests whether a model can recall specific …

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models

Zeyuan Chen, Yihan Ma, Xinyue Shen, Michael Backes et autres

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership inference attack that tests whether a model can recall specific …

de (code pays fourni par la source)

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models

Zeyuan Chen, Yihan Ma, Xinyue Shen, Michael Backes et autres

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership inference attack that tests whether a model can recall specific …

de (code pays fourni par la source)

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models

Zeyuan Chen, Yihan Ma, Xinyue Shen, Michael Backes et autres

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership inference attack that tests whether a model can recall specific …

de (code pays fourni par la source)

Choledochoscope Removal of a Sharp Appendiceal Foreign Body

Y Chen, Wei Chen, Xiaofang Zhou, Yihan Ma

A 73-year-old man presented 3 days after accidental ingestion of a root canal file during endodontic treatment, accompanied by 3 hours of right lower quadrant pain. Laboratory tests were unremarkable. Abdominal computed tomography (Figure 1a) revealed appendiceal wall thickening, a 2.7 cm …

hk, cn (code pays fourni par la source)

Adaptive acoustic streaming microbial system for oxytetracycline removal

Tao Jiang, Xiaotong Si, Yifan Wang, Yihan Ma et autres

cn (code pays fourni par la source)

PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality

Zeyuan Chen, Ziqing Yang, Yihan Ma, Michael Backes et autres

As academic submissions grow, the traditional peer review process struggles to keep up, raising concerns about quality and fairness. A trend of using large language models (LLMs) for assistance has emerged. In this work, we take a critical step toward improving the …

de (code pays fourni par la source)

PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality

Zeyuan Chen, Ziqing Yang, Yihan Ma, Michael Backes et autres

As academic submissions grow, the traditional peer review process struggles to keep up, raising concerns about quality and fairness. A trend of using large language models (LLMs) for assistance has emerged. In this work, we take a critical step toward improving the …

de (code pays fourni par la source)

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions

Yiting Qu, Ziqing Yang, Yihan Ma, Michael Backes et autres

de, nl (code pays fourni par la source)