Scientific Calculator for Designing Trojan Detectors in Neural Networks
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.
Code (1)
Similar Papers 제목 키워드 기반
Scientific calculator project report
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.
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
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
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
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)