Shiqing Ma

TRADER

2020

Recurrent Neural Networks (RNN) can deal with (textual) input with various length and hence have a lot of applications in software systems and software engineering applications. RNNs depend on word embeddings that are usually pre-trained …

AUTOTRAINER: An Automatic DNN Training Problem Detection and Repair System

2021

With machine learning models especially Deep Neural Network (DNN) models becoming an integral part of the new intelligent software, new tools to support their engineering process are in high demand. Existing DNN debugging tools are …

Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense

2022 · arXiv (Cornell University)

We develop a novel optimization method for NLPbackdoor inversion. We leverage a dynamically reducing temperature coefficient in the softmax function to provide changing loss landscapes to the optimizer such that the process gradually focuses on …

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

2023 · arXiv (Cornell University)

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we …

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

2023 · arXiv (Cornell University)

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream …