Search NASASearch

Engineering topics

Nguyen, Truc

Publications and source records attributed to Nguyen, Truc.

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

Despite its significant benefits in enhancing the transparency and trustworthiness of artificial intelligence (AI) systems, explainable AI (XAI) can unintentionally provide adversaries with insights into blackbox models, increasing their vulnerability to various attacks. In this paper, we develop a novel explanation-driven adversarial attack against blackbox classifiers based on feature substitution, called XSub. The key idea of XSub is to strategically replace important features (identified via XAI) in the original sample with corresponding important features of a different label, thereby increasing the likelihood of the model misclassifying the perturbed sample. XSub only requires a minimal number of queries and can be easily extended to launch backdoor attacks in case the attacker has access to the model's training data. Our evaluation shows that XSub is not only effective and stealthy but also low-cost, showcasing its feasibility across a wide range of AI applications.

adversarial attack

SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97]

You've found the official code repository for the paper "SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems," presented at the Foundation Models for Science: Progress, Opportunities, and Challenges workshop at NeurIPS 2024. Our paper conjectures that interfaces (both text templates as well as conversational) makes interacting with simulation surrogate models for complex systems more intuitive and accessible for both non-experts and experts. "System captions", or SysCaps, are text-based descriptions of systems based on information contained in simulation metadata. Our paper's goal is to train multimodal regression models that take text inputs (SysCaps) and timeseries inputs (exogenous system conditions such as hourly weather) and regress timeseries simulation outputs (e.g. hourly building energy consumption). The experiments in our paper with building and wind farm simulators, which can be reproduced using this codebase, aim to help us understand whether a) accurate regression in this setting is possible and b) if so, how well can we do it. Paper: https://arxiv.org/abs/2405.19653

Emami, Patrick

A Numerical Simulation Study to Develop an Acceptable Wake Encounter Boundary for a B737-100 Airplane

The National Aeronautics and Space Administration (NASA) is conducting research with the goal of enabling safe improvements in the capacity of the nation's air transportation system. The wake-vortex upset hazard is an important factor in establishing the minimum safe spacing between aircraft during landing and take-off operations, thus impacting airport capacity. A batch simulation study was conducted to assess the sensitivity of various safe landing criteria in the development of an acceptable wake encounter boundary. A baseline six-degree-of-freedom simulation of a B737-100 airplane was modified to include a wake model and the vortex-induced forces and moments. The guidance and control input for the airplane was provided by an auto-land system. The wake strength and encounter geometry were varied. A sensitivity study was also conducted to assess the effects of encounter modeling methods and accuracy.

Vicroy, Dan D.