activity
20242026
collaborators

5 papers

cs.CV2026

FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence

Xinyu Yan, Boyang Chen, Jiaming Zhang +12

Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual e…

cs.LG2026

SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification

Mingze Ni, Wei Liu

An effective integration of rich feature representations with robust classification mechanisms remains a key challenge in visual understanding tasks. This study introduces two nove…

cs.CL2025

Cross-Entropy Attacks to Language Models via Rare Event Simulation

Mingze Ni, Yongshun Gong, Wei Liu

Black-box textual adversarial attacks are challenging due to the lack of model information and the discrete, non-differentiable nature of text. Existing methods often lack versatil…

cs.CV2024

AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization

Jiyao Li, Mingze Ni, Yifei Dong +2

Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of…

cs.CL2024

Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach

Jiyao Li, Mingze Ni, Yongshun Gong +1

Deep learning underpins most of the currently advanced natural language processing (NLP) tasks such as textual classification, neural machine translation (NMT), abstractive summari…