Neural Trojan

Neural Trojans are malicious backdoors inserted into deep neural networks (DNNs), causing the model to produce erroneous outputs when presented with specific "trigger" inputs while behaving normally otherwise. Current research focuses on developing more sophisticated Trojan attacks that evade detection, including those utilizing logic locking or dormant activation mechanisms, and on creating robust defense mechanisms such as input filtering and sparsity-based detection methods. The vulnerability of DNNs to these attacks poses significant risks to the security and reliability of AI systems across various applications, driving intense research efforts to improve both attack detection and prevention.

Papers

August 15, 2024

A Survey of Trojan Attacks and Defenses to Deep Neural Networks
Lingxin Jin, Xianyu Wen, Wei Jiang, Jinyu Zhan
Deep Neural Network Timely Survey Trojan Attack Neural Trojan

February 12, 2024

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi, Luyao Niu, Bhaskar Ramasubramanian, Bo Li, Radha Poovendran
Game Content Trojan Detection Adaptive Adversary Deep Neural Network Parameter Neural Trojan Trojaned Model

April 12, 2023

Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators
Hongye Xu, Dongfang Liu, Cory Merkel, Michael Zuzak
Logic Reasoning Phantom 2D Accelerator Machine Learning Accelerator Neural Backdoor Neural Trojan Trigger Attack

February 28, 2023

FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
Chong Fu, Xuhong Zhang, Shouling Ji, Ting Wang, Peng Lin, Yanghe Feng, Jianwei Yin
Backdoor Attack Case Relevance Backdoor Detection Neural Trojan

November 2, 2022

Dormant Neural Trojans
Feisi Fu, Panagiota Kiourti, Wenchao Li
Backdoor Attack Backdoor Detection Training Time Attack Trojan Detection Neural Trojan

August 8, 2022

PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
Diego Garcia-soto, Huili Chen, Farinaz Koushanfar
Trojan Attack NLP Application Small Perturbation Trojan Detection Neural Trojan

May 24, 2022

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
Tianlong Chen, Zhenyu Zhang, Yihua Zhang, Shiyu Chang, Sijia Liu, Zhangyang Wang
Sparsity Increase Lottery Ticket Trojan Attack Trojan Detection Neural Trojan Trojan Horse

April 8, 2022

An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks
Xinqiao Zhang, Huili Chen, Ke Huang, Farinaz Koushanfar
Deep Neural Network Backdoor Detection Trojan Detection Neural Trojan

February 24, 2022

Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Kien Do, Haripriya Harikumar, Hung Le, Dung Nguyen, Truyen Tran, Santu Rana, Dang Nguyen, Willy Susilo, Svetha Venkatesh
Trojan Attack Neural Trojan

February 15, 2022

A Survey of Neural Trojan Attacks and Defenses in Deep Learning
Jie Wang, Ghulam Mubashar Hassan, Naveed Akhtar
Deep Learning Artificial Intelligence Timely Survey Trojan Attack Neural Trojan

December 24, 2021

CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing
Haibo Jin, Ruoxi Chen, Jinyin Chen, Yao Cheng, Chong Fu, Ting Wang, Yue Yu, Zhaoyan Ming
Backdoor Attack Fuzz Testing Backdoor Learning Neural Trojan DNN Testing

November 6, 2021

TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework
Bo Lyu, Shiping Wen
Neural Architecture Search Differentiable Architecture Search Differentiable Neural Architecture Search Multi Objective Neural Architecture Search Differentiable Objective Neural Trojan Progressive Neural Architecture Search