Search Results for author:
Found 9 papers, 3 papers with code
Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
Deep learning has shown its power in many applications, including object detection in images, natural-language understanding, and speech recognition.
Smart App Attack: Hacking Deep Learning Models in Android Apps
We evaluate the attack effectiveness and generality in terms of four different settings including pre-trained models, datasets, transfer learning approaches and adversarial attack algorithms.
Training-free Lexical Backdoor Attacks on Language Models
In this work, we propose Training-Free Lexical Backdoor Attack (TFLexAttack) as the first training-free backdoor attack on language models.
HiTSKT: A Hierarchical Transformer Model for Session-Aware Knowledge Tracing
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 performance can be accurately predicted.
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question.
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
We believe that our findings may give light on future efforts to determine and mitigate the ethical hazards posed by machines in LLM applications.
Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps
In particular, our attack could influence the performance and latency of the model without affecting the operation of a DL app.
Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning
In recent years, on-device deep learning has gained attention as a means of developing affordable deep learning applications for mobile devices.
Towards Real Smart Apps: Investigating Human-AI Interactions in Smartphone On-Device AI Apps
We further implemented our findings into a multi-faceted search-enabled gallery.
