173 citations · 211 across the 15 of their papers we have counts for
17 papers
Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
Bo Li, Yue Yang, Yujin Huang +6
Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic gra…
World-as-Graph: Relational World Modeling Through Latent Space Graphs
Yaqi Yang, Shuo Huang, Yujin Huang +3
World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made expressive progress by represe…
SoK: Attack and Defense Landscape of Mobile On-device AI Systems
Yujin Huang, Xin Zheng, Xingliang Yuan +1
Mobile on-device AI (MoAI) systems that integrate locally deployed AI models with conventional mobile software components are emerging as a key paradigm for delivering intelligent…
Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
Shuyu Chang, Haiping Huang, Yanjun Zhang +3
Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a f…
THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
Yujin Huang, Zhi Zhang, Qingchuan Zhao +2
On-device deep learning (DL) has rapidly gained adoption in mobile apps, offering the benefits of offline model inference and user privacy preservation over cloud-based approaches.…
Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction
Yuncheng Hua, Yujin Huang, Shuo Huang +5
This paper tackles the task of emotion-cause pair extraction in the unsupervised domain adaptation setting. The problem is challenging as the distributions of the events causing em…
Pairwise GUI Dataset Construction Between Android Phones and Tablets
Han Hu, Haolan Zhan, Yujin Huang +1
In the current landscape of pervasive smartphones and tablets, apps frequently exist across both platforms. Although apps share most graphic user interfaces (GUIs) and functionalit…
A First Look at On-device Models in iOS Apps
Han Hu, Yujin Huang, Qiuyuan Chen +2
Powered by the rising popularity of deep learning techniques on smartphones, on-device deep learning models are being used in vital fields like finance, social media, and driving a…
Towards Real Smart Apps: Investigating Human-AI Interactions in Smartphone On-Device AI Apps
Jason Ching Yuen Siu, Jieshan Chen, Yujin Huang +2
With the emergence of deep learning techniques, smartphone apps are now embedded on-device AI features for enabling advanced tasks like speech translation, to attract users and inc…
A Pairwise Dataset for GUI Conversion and Retrieval between Android Phones and Tablets
Han Hu, Haolan Zhan, Yujin Huang +1
With the popularity of smartphones and tablets, users have become accustomed to using different devices for different tasks, such as using their phones to play games and tablets to…
Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps
Ye Sang, Yujin Huang, Shuo Huang +1
The increasing popularity of deep learning (DL) models and the advantages of computing, including low latency and bandwidth savings on smartphones, have led to the emergence of int…
Training-free Lexical Backdoor Attacks on Language Models
Yujin Huang, Terry Yue Zhuo, Qiongkai Xu +3
Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor…
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
Terry Yue Zhuo, Zhuang Li, Yujin Huang +4
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question. Recent advancements in few-shot language models tra…
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
Terry Yue Zhuo, Yujin Huang, Chunyang Chen +1
Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretica…
HiTSKT: A Hierarchical Transformer Model for Session-Aware Knowledge Tracing
Fucai Ke, Weiqing Wang, Weicong Tan +4
Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future perfor…
Smart App Attack: Hacking Deep Learning Models in Android Apps
Yujin Huang, Chunyang Chen
On-device deep learning is rapidly gaining popularity in mobile applications. Compared to offloading deep learning from smartphones to the cloud, on-device deep learning enables of…
Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
Yujin Huang, Han Hu, Chunyang Chen
Deep learning has shown its power in many applications, including object detection in images, natural-language understanding, and speech recognition. To make it more accessible to…