Search Results for author: Guanxiong Liu

Found 11 papers, 3 papers with code

An Adaptive Black-box Defense against Trojan Attacks (TrojDef)

no code implementations5 Sep 2022 Guanxiong Liu, Abdallah Khreishah, Fatima Sharadgah, Issa Khalil

Through mathematical analysis, we show that if the attacker is perfect in injecting the backdoor, the Trojan infected model will be trained to learn the appropriate prediction confidence bound, which is used to distinguish Trojan and benign inputs under arbitrary perturbations.

Smart Traffic Monitoring System using Computer Vision and Edge Computing

no code implementations7 Sep 2021 Guanxiong Liu, Hang Shi, Abbas Kiani, Abdallah Khreishah, Jo Young Lee, Nirwan Ansari, Chengjun Liu, Mustafa Yousef

In this paper, we focus on two common traffic monitoring tasks, congestion detection, and speed detection, and propose a two-tier edge computing based model that takes into account of both the limited computing capability in cloudlets and the unstable network condition to the TMC.

Edge-computing Management

A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples

no code implementations3 Sep 2021 Guanxiong Liu, Issa Khalil, Abdallah Khreishah, NhatHai Phan

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan.

Federated Learning Model Poisoning

Trojans and Adversarial Examples: A Lethal Combination

no code implementations1 Jan 2021 Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Hai Phan

In this work, we naturally unify adversarial examples and Trojan backdoors into a new stealthy attack, that is activated only when 1) adversarial perturbation is injected into the input examples and 2) a Trojan backdoor is used to poison the training process simultaneously.

ManiGen: A Manifold Aided Black-box Generator of Adversarial Examples

no code implementations11 Jul 2020 Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Abdulelah Algosaibi, Adel Aldalbahi, Mohammed Alaneem, Abdulaziz Alhumam, Mohammed Anan

Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white-box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-the-art defenses.

Using Single-Step Adversarial Training to Defend Iterative Adversarial Examples

no code implementations22 Feb 2020 Guanxiong Liu, Issa Khalil, Abdallah Khreishah

Single-Step adversarial training methods have been proposed as computationally viable solutions, however they still fail to defend against iterative adversarial examples.

CheXclusion: Fairness gaps in deep chest X-ray classifiers

1 code implementation14 Feb 2020 Laleh Seyyed-Kalantari, Guanxiong Liu, Matthew McDermott, Irene Y. Chen, Marzyeh Ghassemi

We demonstrate that TPR disparities exist in the state-of-the-art classifiers in all datasets, for all clinical tasks, and all subgroups.

Fairness Medical Diagnosis +2

Using Intuition from Empirical Properties to Simplify Adversarial Training Defense

no code implementations27 Jun 2019 Guanxiong Liu, Issa Khalil, Abdallah Khreishah

Due to the surprisingly good representation power of complex distributions, neural network (NN) classifiers are widely used in many tasks which include natural language processing, computer vision and cyber security.

ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural Networks

1 code implementation17 Apr 2019 Guanxiong Liu, Issa Khalil, Abdallah Khreishah

Neural Network classifiers have been used successfully in a wide range of applications.

Clinically Accurate Chest X-Ray Report Generation

1 code implementation4 Apr 2019 Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, Marzyeh Ghassemi

The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care.

Text Generation

GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier

no code implementations6 Mar 2019 Guanxiong Liu, Issa Khalil, Abdallah Khreishah

Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity.

Overall - Test

Cannot find the paper you are looking for? You can Submit a new open access paper.