• Publications
  • Influence
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Identity Mappings in Deep Residual Networks
TLDR
The propagation formulations behind the residual building blocks suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. Expand
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TLDR
This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities. Expand
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
TLDR
This work equips the networks with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale. Expand
Trojaning Attack on Neural Networks
TLDR
A trojaning attack on neuron networks that can be successfully triggered without affecting its test accuracy for normal input data, and it only takes a small amount of time to attack a complex neuron network model. Expand
Accelerating Very Deep Convolutional Networks for Classification and Detection
TLDR
This paper aims to accelerate the test-time computation of convolutional neural networks, especially very deep CNNs, and develops an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient descent (SGD). Expand
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
TLDR
This work equips the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale. Expand
AsDroid: detecting stealthy behaviors in Android applications by user interface and program behavior contradiction
TLDR
This paper uses static program analysis to attribute a top level function that is usually a user interaction function with the behavior it performs, and analyzes the text extracted from the user interface component associated with the toplevel function to detect stealthy behavior. Expand
Z3-str: a z3-based string solver for web application analysis
TLDR
A general purpose string solver, called Z3-str, is developed as an extension of the Z3 SMT solver through its plug-in interface, which treats strings as a primitive type, thus avoiding the inherent limitations observed in many existing solvers that encode strings in terms of other primitives. Expand
High Accuracy Attack Provenance via Binary-based Execution Partition
TLDR
The technique, called BEEP, has negligible runtime overhead (< 1.4%) and low space overhead (12.28% on average) and is effective in capturing the minimal causal graph for every attack case the authors have studied, without any dependence explosion. Expand
...
1
2
3
4
5
...