103 citations · 483 across the 42 of their papers we have counts for
6 papers · 1 filter
Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection
Ruixiang Tang, Mengnan Du, Xia Hu
In this paper, we present DSN (Deep Serial Number), a simple yet effective watermarking algorithm designed specifically for deep neural networks (DNNs). Unlike traditional methods…
A Unified Taylor Framework for Revisiting Attribution Methods
Huiqi Deng, Na Zou, Mengnan Du +3
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to ind…
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Sina Mohseni, Fan Yang, Shiva Pentyala +6
Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale…
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
Ruixiang Tang, Mengnan Du, Ninghao Liu +2
With the widespread use of deep neural networks (DNNs) in high-stake applications, the security problem of the DNN models has received extensive attention. In this paper, we invest…
Mitigating Gender Bias in Captioning Systems
Ruixiang Tang, Mengnan Du, Yuening Li +3
Image captioning has made substantial progress with huge supporting image collections sourced from the web. However, recent studies have pointed out that captioning datasets, such…
Adversarial Attacks and Defenses: An Interpretation Perspective
Ninghao Liu, Mengnan Du, Ruocheng Guo +2
Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. A…