30 Papers
332 Citations
Xiaojun Xu is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Computer science & Robustness (computer science). The author has an hindex of 11, co-authored 23 publications. Previous affiliations of Xiaojun Xu include Shanghai Jiao Tong University.
Chat about Author
Papers
Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection
Xiaojun Xu,Chang Liu,Qian Feng,Heng Yin,Le Song,Dawn Song +5 more
- 30 Oct 2017
TL;DR: This work proposes a novel neural network-based approach to compute the embedding, i.e., a numeric vector, based on the control flow graph of each binary function, then shows that Gemini outperforms the state-of-the-art approaches by large margins with respect to similarity detection accuracy.
•Posted Content
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
Xiaojun Xu,Chang Liu,Dawn Song +2 more
TL;DR: A sketch-based approach where the sketch contains a dependency graph, so that one prediction can be done by taking into consideration only the previous predictions that it depends on, and it is shown that SQLNet can outperform the prior art by 9% to 13% on the WikiSQL task.
Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection
TL;DR: Zhang et al. as discussed by the authors proposed a novel neural network-based approach to compute the embedding, i.e., a numeric vector, based on the control flow graph of each binary function, then the similarity detection can be done efficiently by measuring the distance between the embeddings for two functions.
258
•Posted Content
Detecting AI Trojans Using Meta Neural Analysis
TL;DR: A Meta Neural Trojan Detection pipeline that does not make assumptions on the attack strategies and only needs black-box access to models is introduced and achieves 97% detection AUC score and significantly outperforms existing detection approaches.
226
•Posted Content
RAB: Provable Robustness Against Backdoor Attacks
TL;DR: This paper provides the first benchmark for certified robustness against backdoor attacks, theoretically proves the robustness bound for machine learning models based on this training process, proves that the bound is tight, and derives robustness conditions for Gaussian and Uniform smoothing distributions.
146