paper-with-me

Papers

Trojans in Artificial Intelligence (TrojAI) Final Report

2026-02-06 · Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski, Tim Blattner, Derek Juba, Peter Bajcsy, Antonio Cardone, Philippe Dessauw, Alden Dima, Anthony J. Kearsley, Melinda Kleczynski, Joel Vasanth, Walid Keyrouz, Chace Ashcraft, Neil Fendley, Ted Staley, Trevor Stout, Josh Carney, Greg Canal, Will Redman, Aurora Schmidt, Cameron Hickert, William Paul, Jared Markowitz, Nathan Drenkow, David Shriver, Marissa Connor, Keltin Grimes, Marco Christiani, Hayden Moore, Jordan Widjaja, Kasimir Gabert, Uma Balakrishnan, Satyanadh Gundimada, John Jacobellis, Sandya Lakkur, Vitus Leung, Jon Roose, Casey Battaglino, Farinaz Koushanfar, Greg Fields, Xihe Gu, Yaman Jandali, Xinqiao Zhang, Tara Javidi, Akash Vartak, Tim Oates, Ben Erichson, Michael Mahoney, Rauf Izmailov, Xiangyu Zhang, Guangyu Shen, Siyuan Cheng, Shiqing Ma, XiaoFeng Wang, Haixu Tang, Di Tang, Xiaoyi Chen, Zihao Wang, Rui Zhu, Susmit Jha, Xiao Lin, Manoj Acharya, Weichao Zhou, Feisi Fu, Panagiota Kiourti, Chenyu Wang, Zijian Guo, H M Sabbir Ahmad, Wenchao Li, Chao Chen arxiv

The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors intentionally embedded within an AI model that can cause a system to fail in unexpected ways, or allow a malicious actor to hijack the AI model at will. This multi-year initiative helped to map out the complex nature of the threat, pioneered foundational detection methods, and identified unsolved challenges that require ongoing attention by the burgeoning AI security field. This report synthesizes the program's key findings, including methodologies for detection through weight analysis and trigger inversion, as well as approaches for mitigating Trojan risks in deployed models. Comprehensive test and evaluation results highlight detector performance, sensitivity, and the prevalence of "natural" Trojans. The report concludes with lessons learned and recommendations for advancing AI security research.

📄 PDF Abstract BibTeX arXiv:2602.07152

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

2020-03-13 · Kiran Karra, Chace Ashcraft, Neil Fendley

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize…

Reinforcement Learning

PoTrojan: powerful neural-level trojan designs in deep learning models

2018-02-08 · Minhui Zou, Yang Shi, Chengliang Wang, Fangyu Li 외

With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively s…

Deep Learning

TAD: Trigger Approximation based Black-box Trojan Detection for AI

2021-02-03 · Xinqiao Zhang, Huili Chen, Farinaz Koushanfar

An emerging amount of intelligent applications have been developed with the surge of Machine Learning (ML). Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical di…

Autonomous DrivingMedical Diagnosis

Baseline Pruning-Based Approach to Trojan Detection in Neural Networks

2021-01-22 · Peter Bajcsy, Michael Majurski

This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing systematically pruned NN models. Our pruning-based approach consists of three main steps. First, detect any deviations from the …

A Survey of Trojan Attacks and Defenses to Deep Neural Networks

2024-08-15 · Lingxin Jin, Xianyu Wen, Wei Jiang, Jinyu Zhan

Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their sus…

Autonomous Driving