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

1 code implementation • 12 Nov 2024 • Jiyao Li, Mingze Ni, Yongshun Gong, Wei Liu

Deep learning underpins most of the currently advanced natural language processing (NLP) tasks such as textual classification, neural machine translation (NMT), abstractive summarization and question-answering (QA).

Abstractive Text Summarization Machine Translation +2

AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization

1 code implementation • 19 Feb 2024 • Jiyao Li, Mingze Ni, Yifei Dong, Tianqing Zhu, Wei Liu

This paper presents a novel adversarial attack strategy, AICAttack (Attention-based Image Captioning Attack), designed to attack image captioning models through subtle perturbations on images.

Adversarial Attack Image Captioning

Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service

no code implementations • 12 Dec 2022 • Jiyao Li, Vicki H. Allan

Online ride-hailing services have become a prevalent transportation system across the world.

Deep Reinforcement Learning

A Ride-Matching Strategy For Large Scale Dynamic Ridesharing Services Based on Polar Coordinates

no code implementations • 8 Jun 2019 • Jiyao Li, Vicki H. Allan

We do a case study to identify the best set of parameters of the dynamic ridesharing service with a training set of 135, 252 trip requests.