paper-with-me

홈 › Papers

Scientific Calculator for Designing Trojan Detectors in Neural Networks

2020-06-05 · Peter Bajcsy, Nicholas J. Schaub, Michael Majurski

This work presents a web-based interactive neural network (NN) calculator and a NN inefficiency measurement that has been investigated for the purpose of detecting trojans embedded in NN models. This NN Calculator is designed on top of TensorFlow Playground with in-memory storage of data and NN graphs plus coefficients. It is "like a scientific calculator" with analytical, visualization, and output operations performed on training datasets and NN architectures. The prototype is aaccessible at https://pages.nist.gov/nn-calculator. The analytical capabilities include a novel measurement of NN inefficiency using modified Kullback-Liebler (KL) divergence applied to histograms of NN model states, as well as a quantification of the sensitivity to variables related to data and NNs. Both NN Calculator and KL divergence are used to devise a trojan detector approach for a variety of trojan embeddings. Experimental results document desirable properties of the KL divergence measurement with respect to NN architectures and dataset perturbations, as well as inferences about embedded trojans.

📄 PDF Abstract BibTeX arXiv:2006.03707

Code (1)

usnistgov/nn-calculator 공식 구현 tf

Similar Papers 제목 키워드 기반

Scientific calculator project report

2024-11-20 · Authorea 2024 11 · Kamal Acharya

The project Scientific Calculator is designed to automate the calculation procedure. Making less paper work and automate the process of calculation.

Scientific calculator project report.

2024-08-05 · Authorea 2024 8 · Acharya Kamal

The project Scientific Calculator is designed to automate the calculation procedure. Making less paper work and automate the process of calculation.

TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion

2026-01-23 · Saideep Sreekumar, Zeng Wang, Akashdeep Saha, Weihua Xiao 외 arxiv

Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce TrojanGYM, an agentic, LLM-driven framework t…

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors

2024-02-12 · Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi, Luyao Niu 외

We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-em…

TrojanForge: Generating Adversarial Hardware Trojan Examples Using Reinforcement Learning

2024-05-24 · Amin Sarihi, Peter Jamieson, Ahmad Patooghy, Abdel-Hameed A. Badawy

The Hardware Trojan (HT) problem can be thought of as a continuous game between attackers and defenders, each striving to outsmart the other by leveraging any available means for an advantage. Machine Learning (ML) has r…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)