Search Results for author: Pengcheng Zhang

Found 11 papers, 2 papers with code

RITFIS: Robust input testing framework for LLMs-based intelligent software

no code implementations21 Feb 2024 Mingxuan Xiao, Yan Xiao, Hai Dong, Shunhui Ji, Pengcheng Zhang

To our knowledge, RITFIS is the first framework designed to assess the robustness of LLM-based intelligent software against natural language inputs.

Combinatorial Optimization

A Spatial-Temporal Dual-Mode Mixed Flow Network for Panoramic Video Salient Object Detection

no code implementations13 Oct 2023 Xiaolei Chen, Pengcheng Zhang, Zelong Du, Ishfaq Ahmad

First, the ILA module calculates the attention between adjacent level features of consecutive frames of panoramic video to improve the accuracy of extracting salient object features from the spatial flow.

Object object-detection +3

Towards Fully Decoupled End-to-End Person Search

no code implementations10 Sep 2023 Pengcheng Zhang, Xiao Bai, Jin Zheng, Xin Ning

This enables independent learning for different objectives thus fully decoupled the model for persons earch.

Person Search

LEAP: Efficient and Automated Test Method for NLP Software

1 code implementation22 Aug 2023 Mingxuan Xiao, Yan Xiao, Hai Dong, Shunhui Ji, Pengcheng Zhang

The widespread adoption of DNNs in NLP software has highlighted the need for robustness.

Test

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

1 code implementation17 Jul 2023 Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Stefanos Koffas, Yiming Li

Motivated by these findings, we propose to exploit elements of sound ($e. g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks.

Backdoor Attack speech-recognition +1

Inflection Point: A New Perspective on Photonic Nanojets

no code implementations17 Dec 2020 Guoqiang Gu, Pengcheng Zhang, Sihui Chen, Yi Zhang, Hui Yang

When light propagates through the edge or middle part of microparticle's incoming interface, there is a basic rule that light converges and diverges rapidly or slowly at the output port.

Optics

Quality Assurance Technologies of Big Data Applications: A Systematic Literature Review

no code implementations5 Feb 2020 Pengcheng Zhang, Wennan Cao, Henry Muccini

However, the quality of these applications is far from perfect, leading to a large amount of issues and problems.

Software Engineering

Cannot find the paper you are looking for? You can Submit a new open access paper.