Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

A beautiful, simple, clean, and responsive Jekyll theme for academics

cluster data collected from production clusters in Alibaba for cluster management research

Atlas, a hybrid cloud migration advisor offers migration recommendations with customizable performance, cost and availability trade-offs. Also check our API resource estimation work below.

Also, check our recent DeepRest based hybrid-cloud migration advisor Atlas by clicking on the link below.

Robust Object Detection Fusion Against Deception

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enri…

Perception Poisoning Attacks in Federated Learning

Diversity Optimized Ensemble

Code for Data Poisoning Attacks Against Federated Learning Systems

A log-structured filesystem using S3 for storage and mounted using FUSE

A simplified implemention of Faster R-CNN that replicate performance from origin paper

pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

A Implementation of IJCAI-19(Transferable Adversarial Attacks for Image and Video Object Detection)

Adversarial Examples for Semantic Segmentation and Object Detection

💥Faster R-CNN from scratch written with Keras

A Keras port of Single Shot MultiBox Detector

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously c…

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Benchmarking and Visualization Tool for Adversarial Machine Learning

A challenge to explore adversarial robustness of neural networks on MNIST.

A challenge to explore adversarial robustness of neural networks on CIFAR10.

Latex code for making neural networks diagrams

This project accelerates deep learning models on the edge with the support of running ensemble learning for performance improvement. The current version accelerates YOLO object detectors with Intel…

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams