fhasan8 Goto Github PK

abs

ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation

cs6220-group4-trojandetection

cs7650_project_iglu

evalai

:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI

fhasan8.github.io

gtattackpod

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 crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. This project collects state-of-the-art attack algorithms and organizes them with a easy-to-use interface.

sound-spaces

A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.

soundspaces-challenge

Starter code for SoundSpaces challenge at CVPR 21's Embodied AI workshop

tdc-starter-kit

Starter kit and data loading code for the Trojan Detection Challenge NeurIPS 2022 competition

tog

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-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from untargeted random attacks or even targeted attacks with three types of specificity: (1) object-vanishing, (2) object-fabrication, and (3) object-mislabeling. Apart from tailoring an adversarial perturbation for each input image, we further demonstrate TOG as a universal attack, which trains a single adversarial perturbation that can be generalized to effectively craft an unseen input with a negligible attack time cost. Also, we apply TOG as an adversarial patch attack, a form of physical attacks, showing its ability to optimize a visually confined patch filled with malicious patterns, deceiving well-trained object detectors to misbehave purposefully.