Search NASA⌕ Search

SEARCH · Search NASA

Results for “Adversarial attacks”

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.

At least 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of an ML model, whereas backdoor data poisoning attacks maintain system performance unless the MLmodel is presented with an input containing an embedded“trigger” that provides a predetermined response advantageous to the adversary. Our work builds upon prior back-door data-poisoning research for ML image classifiers and systematically assesses different experimental conditions including types of trigger patterns, persistence of trigger patterns during retraining, poisoning strategies, architectures (ResNet-50, NasNet, NasNet-Mobile), datasets (Flowers, CIFAR-10), and potential defensive regularization techniques (Contrastive Loss, Logit Squeezing, Manifold Mixup,Soft-Nearest-Neighbors Loss). Experiments yield four key findings. First, the success rate of backdoor poisoning at-tacks varies widely, depending on several factors, including model architecture, trigger pattern and regularization technique. Second, we find that poisoned models are hard to detect through performance inspection alone. Third, regularization typically reduces backdoor success rate, although it can have no effect or even slightly increase it, depending on the form of regularization. Finally, backdoors inserted through data poisoning can be rendered ineffective after just a few epochs of additional training on a small set of clean data without affecting the model’s performance.

Truong, Loc T.↗
DOE OSTI2019

Resilient Distributed Parameter Estimation With Heterogeneous Data

This paper studies resilient distributed estimation under measurement attacks. A set of agents each makes successive local, linear, noisy measurements of an unknown vector field collected in a vector parameter. The local measurement models are heterogeneous across agents and may be locally unobservable for the unknown parameter. An adversary compromises some of the measurement streams and changes their values arbitrarily. The agents' goal is to cooperate over a peer-to-peer communication network to process their (possibly compromised) local measurements and estimate the value of the unknown vector parameter. We present SAGE, the Saturating Adaptive Gain Estimator, a distributed, recursive, consensus + innovations estimator that is resilient to measurement attacks. We demonstrate that, as long as the number of compromised measurement streams is below a particular bound, then, SAGE guarantees that all of the agents' local estimates converge almost surely to the value of the parameter. The resilience of the estimator - i.e., the number of compromised measurement streams it can tolerate - does not depend on the topology of the inter-agent communication network. Finally, we illustrate the performance of SAGE through numerical examples.

42 ENGINEERING↗
DOE OSTI2020

Assessing DER Network Cybersecurity Defences in a Power-Communication Co-Simulation Environment

Increasing penetrations of interoperable distributed energy resources (DER) in the electric power system are expanding the power system attack surface. Maloperation or malicious control of DER equipment can now cause substantial disturbances to grid operations. Fortunately, many options exist to defend and limit adversary impact on these newly-created DER communication networks, which typically traverse the public internet. However, implementing these security features will increase communication latency, thereby adversely impacting real-time DER grid support service effectiveness. In this work, a collection of software tools called SCEPTRE were used to create a co-simulation environment where SunSpec-compliant PV inverters were deployed as virtual machines and interconnected to simulated communication network equipment. Network segmentation, encryption, and moving target defence security features were deployed on the control network to evaluate their influence on cybersecurity metrics and power system performance. The results indicated that adding these security features did not impact DER-based grid control systems but improved the cybersecurity posture of the network when implemented appropriately.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Typing Discipline for High-Assurance Control Systems

This poster describes a typing discipline for high-assurance industrial systems based on three novel type systems. The first type system, information flow control (IFC), controls the flow of data through the system. The second system, dependent session types, restricts messages exchanged during the execution of a communication protocol to avoid dangerous states. The third system uses dimensional analysis to avoid subtle bugs that adversaries can exploit to cause the system to enter a dangerous state. This poster describes how a combination of these approaches can prevent sophisticated cyber attacks, such as the infamous Stuxnet incident, from occurring. In addition, we provide experimental evidence to support the claim that these approaches can be applied in control systems that are resource-constrained.

42 - ENGINEERING↗
DOE OSTI2025

Modeling Cyber Supply Chain Incidents with Multilayered Graph Motifs

As noted within the literature, supply chain includes people and organizations---manufacturers, integrators, and third-party vendors---that are involved in one or more stages of a product lifecycle. Since supply chains, by definition, include organizations and people, supply chain risk management activities must consider dependencies between an organization's business processes and third-party resources. Just as adversarial tactics can be implemented via techniques implemented via networked computer systems, so can such tactics be expressed via legal business relationships. A cyber incident may have an exponential impact downstream, for example, by leveraging a product's distribution channel (e.g. malicious updates in SolarWinds, buggy updates in CrowdStrike). Similarly, legitimate and legal business relationships also affect the attack surface exposure of systems, enabling long-term persistence and/or unknown impacts to product quality that are hard to detect. This paper catalogs several recent digital supply chain incidents and applies a multilayered network formalism to develop structural indicators (graph motifs) that reflect potentially-adversarial behavior. Finally, we compare and contrast the characteristics of adversarial tactics (e.g. Loss of Availability, Data Collection) that leverage cyber-physical dependencies to those that leverage legal organizational relationships.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Identifying Adversarial Cyber-Activity in Operational Technology Environments Using Bayesian Networks

Critical infrastructure and other operational technology (OT) environments face increasing cybersecurity risks from adversarial behavior. This paper describes the development of a risk model using a Bayesian network to enhance the comprehension of observable cyber events caused by malicious activity in OT environments. The core of the Bayesian network is a process model that describes the stages of adversary behavior. The remainder of the model is based on the MITRE ATT&CK® for Industrial Control Systems (ICS) taxonomy, which includes tactics and techniques that may be used by the adversary. The observables provide evidence for adversary behavior through the intermediary technique and tactic nodes. One challenge in constructing this model is a lack of open-source data from cyber-attacks on OT systems. This paper discusses learning from limited data, the elicitation of expert opinion to construct the conditional probability tables when data is scarce, and the refinement of the most difficult conditional probabilities tables using several forms of sensitivity analyses. Finally, the Bayesian network is demonstrated using two historical case studies: the DarkSide ransomware attack on the Colonial Pipeline and the destructive cyberattack targeting the ThyssenKrupp blast furnace. Index Terms—Cybersecurity, industrial control systems, operational technology

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Cyber-Informed Engineering Adoption in University Engineering Programs: An Overview of CIE Integration Successes at Nine U.S. Educational Institutions

This report examines the adoption of Cyber-Informed Engineering (CIE) in university engineering programs, driven by the need to protect critical energy infrastructure from adversarial threats. CIE equips current and future engineers and technicians with the necessary mindset, skills, and competencies to enhance the resilience of engineered systems against cyber attacks. This report highlights nine academic partners who are incorporating CIE into their curricula through various approaches, including lectures, courses, and certificates.

42 ENGINEERING↗
DOE OSTI2026

Ensemble Federated Machine Learning‐Based Cybersecurity Situational Awareness in Microgrid Network

Cyber-physical microgrids are vulnerable to stealthy cybersecurity threats that disguise their actions through the exploitation of system knowledge. Such actions can severely impacts microgrids deployed in defense bases, slowing the response time of military forces during national emergencies. Several machine-learning algorithms have been proposed to detect intrusions in the grid networks; however, these traditional machine-learning algorithms lack data privacy and are subject to several adversarial machine-learning threats. This paper proposes a novel federated machine learning (FML)-based three-model framework to detect and identify stealthy data-integrity attacks while ensuring data privacy in microgrid networks. The proposed architecture uses a variational mode decomposition technique to extract derived features from incoming measurement and control datasets. The extraction of these derived features allows FML models to learn minute variations in data patterns that allow them to perform significantly better than the models trained with generic datasets consisting of raw features. Our experimental results show the efficient performance of the proposed methodology against different types of data integrity attacks while considering primary and secondary controllers in microgrids. Further, the applied FML-integrated random forest ensemble algorithm outperforms the existing generic FML algorithms during noisy and noise-free datasets with prediction latencies of only 91–134 µs per sample within the 0.1 s sampling interval and requires communication bandwidth of around ∼8.25 KB/s at the control center and ∼2.7 KB/s per edge client for communication.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2019

Coherency-Based Detection Algorithm for Synchrophasor Cyberattacks

The wide area monitoring system (WAMS) is critical for power system situational awareness, but represents a growing cybersecurity vulnerability. Malicious adversaries may seek to compromise one or more PMUs in order to effect control decisions that unnecessarily disrupt typical grid operations. One example of a particularly pernicious attack vector is the spoofing or replaying of a fault event using one or more compromised PMUs. This work documents the development and validation of a coherency-based cyberattack detection algorithm that integrates a sliding-window singular value decomposition (SVD) with physics-based partitioning analysis to achieve accurate classification of events. Special consideration is given to discerning a sophisticated fault-replay or fault spoofing attack from actual faults. A software-based cybersecurity testbed has been developed for rigorous testing of the algorithm. The algorithm is further validated using simulated synchrophasor datasets obtained from a MinniWECC 63-bus test system. Results show that the algorithm can successfully detect fault-replay attacks even when over half of the PMUs are compromised.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2011

Insecurity of position-based quantum-cryptography protocols against entanglement attacks

Recently, position-based quantum cryptography has been claimed to be unconditionally secure. On the contrary, here we show that the existing proposals for position-based quantum cryptography are, in fact, insecure if entanglement is shared among two adversaries. Specifically, we demonstrate how the adversaries can incorporate ideas of quantum teleportation and quantum secret sharing to compromise the security with certainty. The common flaw to all current protocols is that the Pauli operators always map a codeword to a codeword (up to an irrelevant overall phase). We propose a modified scheme lacking this property in which the same cheating strategy used to undermine the previous protocols can succeed with a rate of at most 85%. We prove the modified protocol is secure when the shared quantum resource between the adversaries is a two- or three-level system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Robustness of deep learning algorithms in astronomy -- galaxy morphology studies

Deep learning models are being increasingly adopted in wide array of scientific domains, especially to handle high-dimensionality and volume of the scientific data. However, these models tend to be brittle due to their complexity and overparametrization, especially to the inadvertent adversarial perturbations that can appear due to common image processing such as compression or blurring that are often seen with real scientific data. It is crucial to understand this brittleness and develop models robust to these adversarial perturbations. To this end, we study the effect of observational noise from the exposure time, as well as the worst case scenario of a one-pixel attack as a proxy for compression or telescope errors on performance of ResNet18 trained to distinguish between galaxies of different morphologies in LSST mock data. We also explore how domain adaptation techniques can help improve model robustness in case of this type of naturally occurring attacks and help scientists build more trustworthy and stable models.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Precursor Analysis Report: Doppelpaymer Ransomware Attack on Petroleos Mexicanos (PEMEX) 2019

The DoppelPaymer Ransomware Attack on Petroleos Mexicanos (PEMEX) 2019 Precursor Analysis Report leverages publicly available information about the PEMEX cyber attack and catalogs anomalous observables for each technique employed in the attack. This analysis is based upon the methodology of the Cybersecurity for the Operational Technology Environment (CyOTE) program. The 2019 DoppelPaymer ransomware attack on PEMEX, Mexico’s nationalized petroleum corporation, highlights a unique threat that ransomware and cybercriminal extortion poses to Operational Technology (OT) environments in critical infrastructure. The incident began with an employee downloading commodity malware that allowed adversaries to gain initial access to PEMEX’s enterprise environment. After conducting privilege escalation, tool ingress, and data exfiltration, the adversaries deployed DoppelPaymer ransomware throughout the PEMEX enterprise environment, resulting in the company having to take dozens of systems offline for at least several days. Although PEMEX stated that their operations were not affected, the data exfiltrated from PEMEX was made available for download on DoppelPaymer’s leak site, as well as on other illicit criminal forums. This stolen data included not only company information, but also sensitive OT-specific configuration data. This incident showcases how cybercriminal exfiltration and posting of sensitive OT architecture documentation can pose security concerns for the targeted organization for years due to the long lifespan of OT assets and architectures. Researchers and analysts identified 18 unique techniques utilized during the attack with a total of 190 observables using MITRE ATT&CK® for Industrial Control Systems. The CyOTE program assesses observables accompanying techniques used prior to the triggering event to identify opportunities to detect malicious activity. If observables accompanying the attack techniques are perceived and investigated prior to the triggering event, earlier comprehension of malicious activity can take place. Fifteen of the identified techniques used during the DoppelPaymer ransomware attack were precursors to the triggering event. Analysis identified 163 observables associated with these precursor techniques, 34 of which were assessed to have an increased likelihood of being perceived in the 60 days preceding the triggering event. The response and comprehension time could have been reduced if the observables had been identified earlier. The information gathered in this report contributes to a library of observables tied to a repository of artifacts, data sources, and technique detection references for practitioners and developers to support the comprehension of indicators of attack. Asset owners and operators can use these products if they experience similar observables or to prepare for comparable scenarios.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2019

Adversarial Artificial Intelligence: State of the Malpractice

Warfare systems are increasingly being supported by artificial intelligence (AI), and its influence is growing. As AI becomes a warfare enabler it has also become a target. For example, AI-enabled machine vision systems can be trivially deceived by specially formulated camouflage. Many approaches to making AI more resilient to protect against specific attacks fail to generalize. However, attacks often do generalize across models trained for the same task, regardless of architecture or training data. This paper will illustrate the state of the practice in offensive and defensive AI and clarify some myths about AI's triumphs and failures in the real world.

Artificial intelligence, AI, cybersecurity, milita↗
DOE OSTI2018

Integrated Cyber/Physical Grid Resiliency Modeling

This project explored coupling modeling and analysis methods from multiple domains to address complex hybrid (cyber and physical) attacks on mission critical infrastructure. Robust methods to integrate these complex systems are necessary to enable large trade-space exploration including dynamic and evolving cyber threats and mitigations. Reinforcement learning employing deep neural networks, as in the AlphaGo Zero solution, was used to identify "best" (or approximately optimal) resilience strategies for operation of a cyber/physical grid model. A prototype platform was developed and the machine learning (ML) algorithm was made to play itself in a game of 'Hurt the Grid'. This proof of concept shows that machine learning optimization can help us understand and control complex, multi-dimensional grid space. A simple, yet high-fidelity model proves that the data have spatial correlation which is necessary for any optimization or control. Our prototype analysis showed that the reinforcement learning successfully improved adversary and defender knowledge to manipulate the grid. When expanded to more representative models, this exact type of machine learning will inform grid operations and defense - supporting mitigation development to defend the grid from complex cyber attacks! This same research can be expanded to similar complex domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

GPLADD: Quantifying Trust in Government and Commercial Systems A Game-Theoretic Approach

Trust in a microelectronics-based system can be characterized as the level of confidence that a system is free of subversive alterations made during system development, or that the development process of a system has not been manipulated by a malicious adversary. Trust in systems has become an increasing concern over the past decade. This report introduces a novel game-theoretic framework, called GPLADD (Graph-based Probabilistic Learning Attacker and Dynamic Defender), for analyzing and quantifying system trustworthiness at the end of the development process, through the analysis of risk of development-time system manipulation. GPLADD represents attacks and attacker-defender contests over time. Here, time is an explicit constraint and allows incorporating the informational asymmetries between the attacker and defender into analysis. GPLADD includes an explicit representation of attack steps via multi-step attack graphs, attacker and defender strategies, and player actions at different times. GPLADD allows quantifying the attack success probability over time and the attacker and defender costs based on their capabilities and strategies. This ability to quantify different attacks provides an input for evaluation of trust in the development process. We demonstrate GPLADD on an example attack and its variants. We develop a method for representing success probability for arbitrary attacks and derive an explicit analytic characterization of success probability for a specific attack. We present a numeric Monte Carlo study of a small set of attacks, quantify attack success probabilities, attacker and defender costs, and illustrate the options the defender has for limiting the attack success and improving trust in the development process.

37 attack↗
DOE OSTI2025

Precursor Analysis Report: Blackmatter Ransomware Attack on New Cooperative 2021

The BlackMatter Ransomware Attack on New Cooperative 2021 Precursor Analysis Report leverages publicly available information about the New Cooperative cyber attack and catalogs anomalous observables for each technique employed in the attack. This analysis is based upon the methodology of the Cybersecurity for the Operational Technology Environment (CyOTE) program. The BlackMatter ransomware was first identified in July 2021 and is reported to have infected more than 50 corporations around the world. , The Iowa-based grain cooperative, New Cooperative, was impacted by the BlackMatter ransomware on or before 18 September 2021. The adversary likely resided on New Cooperative’s networks for 15 days prior to encrypting its network and demanding New Cooperative pay $5.9 million in ransom by 25 September to unlock systems and prevent 1 terabyte (TB) of sensitive data from being publicly released. It is not clear if New Cooperative paid the ransom. The full impact of the ransomware attack is not known; however, according to New Cooperative’s general manager, the attack caused the company’s automated processes to revert back to processes used in the 1970s. , As of 6 October, only 50 percent of New Cooperative’s operations were utilizing automated processes. The company took eight weeks to rebuild the entire network and information technology (IT) systems from the ground up, which puts the date of fully recovery around 13 November. Researchers and analysts identified 20 unique techniques utilized during the attack with a total of 404 observables using MITRE ATT&CK® for Industrial Control Systems. The CyOTE program assesses observables accompanying techniques used prior to the triggering event to identify opportunities to detect malicious activity. If observables accompanying the attack techniques are perceived and investigated prior to the triggering event, earlier comprehension of malicious activity can take place. Seventeen of the identified techniques used during the New Cooperative cyber attack were precursors to the triggering event. Analysis identified 360 observables associated with these precursor techniques, 284 of which were assessed to have an increased likelihood of being perceived in the 15 days preceding the triggering event. The response and comprehension time could have been reduced if the observables had been identified earlier. The information gathered in this report contributes to a library of observables tied to a repository of artifacts, data sources, and technique detection references for practitioners and developers to support the comprehension of indicators of attack. Asset owners and operators can use these products if they experience similar observables or to prepare for comparable scenarios.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗