paper-with-me

Papers

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 reference look-up tables of model file sizes and model graphs. Next, measure the accuracy of a set of systematically pruned NN models following multiple pruning schemas. Finally, classify a NN model as clean or poisoned by applying a mapping between accuracy measurements and NN model labels. This work outlines a theoretical and experimental framework for finding the optimal mapping over a large search space of pruning parameters. Based on our experiments using Round 1 and Round 2 TrojAI Challenge datasets, the approach achieves average classification accuracy of 69.73 % and 82.41% respectively with an average processing time of less than 60 s per model. For both datasets random guessing would produce 50% classification accuracy. Reference model graphs and source code are available from GitHub.

📄 PDF Abstract BibTeX arXiv:2101.12016

Code (2)

usnistgov/trojai-baseline-pruning 공식 구현 pytorch
usnistgov/trojai-literature 공식 구현

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

2022-05-24 · CVPR 2022 1 · Tianlong Chen, Zhenyu Zhang, Yihua Zhang, Shiyu Chang 외

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect …

Network Pruning

Topological Detection of Trojaned Neural Networks

2021-06-11 · NeurIPS 2021 12 · Songzhu Zheng, Yikai Zhang, Hubert Wagner, Mayank Goswami 외

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can lat…

Trojan Detection in Large Language Models: Insights from The Trojan Detection Challenge

2024-04-21 · Narek Maloyan, Ekansh Verma, Bulat Nutfullin, Bislan Ashinov

Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, but their vulnerability to trojan or backdoor attacks poses significant security risks. This paper explores the challenges and in…

Hardware Trojan Detection Using Controlled Circuit Aging

2020-04-06 · Virinchi Roy Surabhi, Prashanth Krishnamurthy, Hussam Amrouch, Kanad Basu 외

This paper reports a novel approach that uses transistor aging in an integrated circuit (IC) to detect hardware Trojans. When a transistor is aged, it results in delays along several paths of the IC. This increase in del…

Game of Trojans: A Submodular Byzantine Approach

2022-07-13 · Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu, Bo Li 외

Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attackers have been shown to be effective aga…