Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adversarial attack”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

207 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Engineering in Cyber Resilience with Cyber-Informed Engineering

Engineers have super powers to provide cybersecurity resilience with deterministic engineering solutions and to protect systems from the most catastrophic consequences that a cyber saboteur could cause. Come to this session to learn how to use engineering risk management skills to harden your engineered systems from cyberattacks. Objective 1 Identify what system functions could be digitally induced to cause undesired high-impact consequences. Objective 2 Analyze how loss or instability of digital controls in a subsystem could lead to high-impact consequences. Objective 3 Analyze how loss or instability in the digital connectivity between systems could lead to high-impact consequences. Objective 4 Identify engineering controls which could build resilience by eliminating digital loss or instability pathways or reduce the impact of digital loss or instability. This presentation will introduce Cyber-Informed Engineering, described below, and walk participants through specific engineering use cases to show how engineers can consider the potential for cyber sabotage in their existing system designs and enact deterministic engineering-based controls which eliminate pathways for attack or mitigate specific consequences. A wide variety of application use cases will be considered so that audience members can align the material with familiar engineering applications. CIE is an engineering approach that integrates cyber resilience into the conception, design, build, and operation of any physical system that has digital connectivity, sensors, monitoring, or control. CIE offers the opportunity to use engineering to eliminate or mitigate avenues for cyber attack—starting from the earliest stage of design and continuing throughout the system’s lifecycle. Today, engineers and industrial control system (ICS) technicians build engineered systems with specific goals for safety, reliability, and functionality. While systems engineering includes considerable safety and failure mode analysis, cybersecurity risks are often not specifically addressed—particularly the risks of intentional cyber compromise, exploitation, and misuse. Cyber-Informed Engineering pairs well with traditional cyber defenses and offers an extra designed-in protection to eliminate the most catastrophic consequences which can be realized by an adversary should traditional cyber defenses fail.

42 ENGINEERING↗
DOE OSTI2023

Quantum Key Distribution for Critical Infrastructures: Towards Cyber-Physical Security for Hydropower and Dams

Hydropower facilities are often remotely monitored or controlled from a centralized remote control room. Additionally, major component manufacturers monitor the performance of installed components, increasingly via public communication infrastructures. While these communications enable efficiencies and increased reliability, they also expand the cyber-attack surface. Communications may use the internet to remote control a facility’s control systems, or it may involve sending control commands over a network from a control room to a machine. The content could be encrypted and decrypted using a public key to protect the communicated information. These cryptographic encoding and decoding schemes become vulnerable as more advances are made in computer technologies, such as quantum computing. In contrast, quantum key distribution (QKD) and other quantum cryptographic protocols are not based upon a computational problem, and offer an alternative to symmetric cryptography in some scenarios. Although the underlying mechanism of quantum cryptogrpahic protocols such as QKD ensure that any attempt by an adversary to observe the quantum part of the protocol will result in a detectable signature as an increased error rate, potentially even preventing key generation, it serves as a warning for further investigation. In QKD, when the error rate is low enough and enough photons have been detected, a shared private key can be generated known only to the sender and receiver. We describe how this novel technology and its several modalities could benefit the critical infrastructures of dams or hydropower facilities. The presented discussions may be viewed as a precursor to a quantum cybersecurity roadmap for the identification of relevant threats and mitigation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Understanding How Organizations Handle Cybersecurity

If there is anything we can learn from the media, it is the frequency and severity of cyber-attacks is increasing and there are not enough qualified people to combat the risk organizations are facing. Current estimates say there are 3.5 million available cybersecurity related jobs globally and there has been a 350% growth in cybersecurity jobs since 2013 (Group, 2020). The Idaho Cyber Research Project (ICRP) is focused on finding an implementing solution to the problems in the workforce development pipeline. Our team consists of Cohort 2 of the ICRP, we are tasked with solving issues faced by organizations hiring new cyber personnel. To provide solutions to these issues we focused our research on four components of workforce availability and competency: resume and transcript analysis, apprenticeships, cyber incident response plan development, and adversarial mindset training. From this research we have produced the following focus areas and subsequent steps for each component of workforce capability: transcript and knowledge skills abilities (KSA) focused analysis, cybersecurity apprenticeships programs, the value of an adversarial mindset, and a guide to setting up cyber incident response plans for underprepared organizations. These solutions can be further developed and implemented to reduce the gap in workforce demand and talent.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Revisiting Current Paradigms: Subject Matter Expert Views on High Consequence Facility Security Assessments

Security assessments support decision-makers' ability to evaluate current capabilities of high consequence facilities (HCF) to respond to possible attacks. However, increasing complexity of today's operational environment requires a critical review of traditional approaches to ensure that implemented assessments are providing relevant and timely insights into security of HCFs. Using interviews and focus groups with diverse subject matter experts (SMEs), this study evaluated the current state of security assessments and identified opportunities to achieve a more "ideal" state. The SME-based data underscored the value of a systems approach for understanding the impacts of changing operational designs and contexts (as well as cultural influences) on security to address methodological shortcomings of traditional assessment processes. These findings can be used to inform the development of new approaches to HCF security assessments that are able to more accurately reflect changing operational environments and effectively mitigate concerns arising from new adversary capabilities.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do these defenses defend? This work considers common approaches to defending learned systems and how security defenses result in performance inequities across different sub-populations. We outline appropriate parity metrics for analysis and begin to answer this question through empirical results of the fairness implications of machine learning security methods. We find that many methods that have been proposed can cause direct harm, like false rejection and unequal benefits from robustness training. The framework we propose for measuring defense equality can be applied to robustly trained models, preprocessing-based defenses, and rejection methods. We identify a set of datasets with a user-centered application and a reasonable computational cost suitable for case studies in measuring the equality of defenses. In our case study of speech command recognition, we show how such adversarial training and augmentation have non-equal but complex protections for social subgroups across gender, accent, and age in relation to user coverage. We present a comparison of equality between two rejection-based defenses: randomized smoothing and neural rejection, finding randomized smoothing more equitable due to the sampling mechanism for minority groups. This represents the first work examining the disparity in the adversarial robustness in the speech domain and the fairness evaluation of rejection-based defenses.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2020

A data analytical approach for assessing the efficacy of Operational Technology active defenses against insider threats

In recent years, the need for Operational Technology (OT) defenses has been recognized, serving as an additional line of defense when Information Technology (IT) defenses are bypassed. This is no longer considered an uncommon possibility when dealing with advanced persistent threat (APT) actors expected to be state-sponsored and receiving insider assistance. In these extreme adversarial situations, OT defenses aim to provide another layer of defense for the system, introduced directly at the physical process level, as described by the sensors data, the system model, and control actions. Just like IT defenses, two schools of thought, i.e., passive and active defenses, have emerged to address this challenge. In active defenses, representing the focus of this paper, known signatures, synthesized based on the system's unique characteristics, are inserted into the system. In contradistinction, passive methods rely solely on observing system behavior in search of patterns of normal behavior with deviations thereof representing abnormal behavior. In their most sophisticated implementations, both passive and active defenses rely on the use of data analytics to identify the patterns and synthesize the observed and/or inserted signatures. Past research has shown that passive defenses may be bypassed by APT actors relying on data analytics and their intimate knowledge of the system to evade detection by respecting the patterns identified by the defenders. Here this manuscript explores the use of active defenses under the assumption that the attacker has privileged access to the system, including access to the system's model and sensors data. Specifically, this manuscript assesses the ability of active defenses to remain invisible to the attackers, and discusses the associated challenges that must be addressed to ensure their resiliency against APT actors.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2025

Enterprise Artificial Intelligence Strategy for Los Alamos National Laboratory

In the 1984 martial arts drama film, The Karate Kid, a young Daniel LaRusso is unexpectedly placed in an adversarial environment unable to eYectively adapt to a series of new threats and limitations. Fortunately for the main character, once placed under the tutelage of a Mr. Miyagi, he finds resiliency not through the adoption of new tools, but a re-focused set of fundamentals. Much in the same way that Daniel learns waxing on and buYing oY car wax by hand has rewards for Karate, LANL is choosing the harder path of self-hosting Large Language Models (LLMs) for enterprise use instead of only relying on buying access to a hosted AI service like Azure’s OpenAI Application Programming Interface (API). We also are not willing to wait for software-as-a-service (SAAS) AI services to meet us where we need to be from a FedRAMP accreditation standpoint. Our operations regularly depend on access at CUI, UCNI, ITAR and other FIPS-199 moderate-impact data levels and hosting our own services gives us the right security and compliance posture to be useful across the broad range of our work at LANL. With the rise in threats to critical infrastructure, cloud service providers (CSPs), and supply chain attacks from both state and non-state actors, we are not placing the bet that SAAS hosted AI services will be available when we need them. Should a major event occur, we do not want our staY and operations left without a pathway for us to fix the problem and resume the use of AI tools.

42 ENGINEERING↗
DOE OSTI2026

Resilience Measurement Framework For Post-deployment Artificial Intelligence (ai) Integrated Systems

Resilience is largely defined as the ability to adapt or recover from adverse conditions, stresses, attacks, or compromises on systems that use or are enabled by digital resources. In Artificial Intelligence Management and Research for Advanced Networked Testbed Hub (AMARANTH), resilience is measured in the amount of time it took from the beginning of a testing period for the model to reach predictions outside of the original 95% confidence interval or using the Kullback-Leibler (KL) divergence theorem, the Population Stability Index (PSI), and traditional methods such as root mean squared error (RMSE) threshold. Artificial Intelligence (AI) model drift is of significant concern when deploying AI-integrated systems into critical and/or secure environments. Drift can impact resilience of the AI-integrated system post-deployment and requires consistent maintenance and upkeep to ensure the model is accurate and precise. To quantify model drift and predict the point when a model's drift becomes unacceptable, we describe using Kullback-Leibler (KL) divergence, Population Stability Index (PSI) and/or confidence interval width estimations to determine the point of failure and time to failure of a model post-deployment. Through simple code functions, the KL-divergence, PSI, confidence interval, and root mean squared (RMSE) point of failures can be used to derive when a model needs to be maintained as well as the impact of adversarial action through statistical means.

Yockey, Patience [Idaho National Laboratory (INL),↗
DOE OSTI2023

Multi-level optimization with the koopman operator for data-driven, domain-aware, and dynamic system security

Cyber-Physical Systems (CPSs) like the power grid are critically important but also increasingly vulnerable; ensuring reliable system operation in the face of disruptions is becoming more and more challenging. Multi-Level Optimization (MLO) is a powerful way to model adversarial interactions, which naturally makes it applicable to studying CPS security. However, MLO typically does not address underlying system dynamics, and incorporating nonlinear dynamics is generally infeasible. In this paper, we show how to combine MLO with the Koopman Operator (KO) to remedy this. The KO maps nonlinear dynamics to a lifted space in which those dynamics are linear, thus making it ideal for use with MLO. Moreover, the structure of the KO also provides convenient ways to incorporate domain knowledge into the data-driven process of learning the KO representation of a given system. Here we then demonstrate the use of MLO-KO on a small example problem taken from the power grid domain, discuss the scalability and computational cost of MLO-KO, and identify future research directions for this work.

42 ENGINEERING↗