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.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗
DOE OSTI2023

Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

In overhead image segmentation tasks, including additional spectral bands beyond the traditional RGB channels can improve model performance. However, it is still unclear how incorporating this additional data impacts model robustness to adversarial attacks and natural perturbations. For adversarial robustness, the additional in-formation could improve the model’s ability to distinguish malicious inputs, or simply provide new attack avenues and vulnerabilities. For natural perturbations, the additional information could better inform model decisions and weaken perturbation effects or have no significant influence at all. In this work, we seek to characterize the performance and robustness of a multispectral (RGB and near infrared) image segmentation model subjected to adversarial attacks and natural perturbations. While existing adversarial and natural robustness research has focused primarily on digital perturbations, we prioritize on creating realistic perturbations designed with physical world conditions in mind. For adversarial robustness, we focus on data poisoning attacks whereas for natural robustness, we focus on extending ImageNet-C common corruptions for fog and snow that coherently and self-consistently perturbs the input data. Overall, we find both RGB and multispectral models are vulnerable to data poisoning attacks regardless of input or fusion architectures and that while physically-realizable natural perturbations still degrade model performance, the impact differs based on fusion architecture and input data.

Deep learning, multispectral images, multimodal fu↗
DOE OSTI2024

AdvEP

AdvEP is a code repository which contains PyTorch implementations of various adversarial attacks on a deep neural network trained with Equilibrium Propagation (EP), which is a neuromorphic learning framework. AdvEP allows for the training, testing, and conducting white/black-box attacks of EP models on a wide variety of applications and datasets. AdvEP is based on the open-source code https://github.com/Laborieux-Axel/Equilibrium-Propagation which was developed to train energy models. AdvEP was created by modifying the original code to perform and test against adversarial attacks. AdvEP was developed in Python, a high-level programming language that takes advantage of the Python ecosystem of high-quality open-source packages for machine learning. AdvEP interfaces heavily with the open-source PyTorch Python package as well as the open-source Adversarial Robustness Toolbox (ART) package.

Mansingh, Siddarth↗
DOE OSTI2023

AdversarialTensors

This library builds a framework for defending ML models against adversarial attacks. The library will be developed at various stages leading to publication and software release at each stage. We employ tensor decomposition strategies as preprocessing stages for the first stage to provide robustness against the prominent adversarial noise. In the second stage, we develop a latent noise generator capable of generating novel adversarial noise that threatens the existing state-of-the-art defense strategy. In the third stage, we develop a UNSUP-GAN model, where the generator is trained to denoise against latent noise and most adversarial noises. This generator can provide a robust adversarial attack against any unseen attack.

Bhattarai, Manish↗
DOE OSTI2021

Evaluating Deception Detection Model Robustness To Linguistic Variation

With the increasing use of automated, machine learning-driven tools and the downstream impact that algorithmic judgements can have, it is critical to develop models that are robust to evolving or manipulated inputs. Evaluating the reliability of multimodal models across linguistic variations to understand model susceptibility to intentional linguistic adversarial attacks as well as natural linguistic variations is essential in this pursuit. We present extensive analysis of model robustness and susceptibility to linguistic variations in the setting of deceptive news detection, a difficult classification task that is an increasingly important problem to solve with the impact of misinformation spread online. We evaluate the effectiveness of incorporating adversarial defense strategies and measure model susceptibility to state-of-the-art adversarial attacks using two types of linguistic attacks — character and word perturbations. We consider two multiclass prediction tasks — a 3-way classification of tweets as trustworthy, propaganda, or disinformation; and a 4-way classification as clickbait, hoax, satire, or conspiracy — and compare the performance of three embeddings that have been state-of-the-art for several NLP tasks — GloVe, ELMo, and BERT — to highlight consistent trends in susceptibility, high confidence misclassifications, and high impact failures. We find that character or mixed ensemble models are the most effective defense mechanisms and that character perturbations are a more effective attack than word perturbations for deception classification.

adversarial evaluation↗
DOE OSTI2023

Certifiably Robust Neural ODE With Learning-Based Barrier Function

Neural Ordinary Differential Equations (ODEs) have gained traction in many applications. While recent studies have focused on empirically increasing the robustness of neural ODEs against natural or adversarial attacks, certified robustness is still lacking. In this work, we propose a framework for training a neural ODE using barrier functions and demonstrate improved robustness for classification problems. Finally, we further provide the first generalization guarantee of robustness against adversarial attacks using a wait-and-judge scenario approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Community detection robustness of graph neural networks

Graph neural networks (GNNs) are increasingly widely used for community detection in attributed networks. They combine structural topology with node attributes through message passing and pooling. However, their robustness or lack thereof with respect to different perturbations and targeted attacks in conjunction with community detection tasks is not well understood. To shed light on latent mechanisms behind GNN sensitivity on community detection tasks, we conduct a systematic computational evaluation of six widely adopted GNN architectures graph convolutional network, graph attention network, graph sample and aggregate (GraphSAGE), differentiable pooling (DiffPool), minimum cut pooling (MinCUT), and deep modularity networks (DMoN). The analysis covers three perturbation categories: node attribute manipulations, edge topology distortions, and adversarial attacks. We use element-centric similarity as the evaluation metric on synthetic benchmarks and real-world citation networks. Our findings indicate that supervised GNNs tend to achieve higher baseline accuracy, while unsupervised methods, particularly DMoN, maintain stronger resilience under targeted and adversarial perturbations. Furthermore, robustness appears to be strongly influenced by community strength, with well-defined communities reducing performance loss. Across all models, node attribute perturbations associated with targeted edge deletions and shifts in attribute distributions tend to cause the largest degradation in community recovery. These findings highlight important trade-offs between accuracy and robustness in GNN-based community detection and offer insights into selecting architectures resilient to noise and adversarial attacks.

Goel, Jaidev [Virginia Polytechnic Inst. and State↗
DOE OSTI2024

Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images

Machine learning models are known to be vulnerable to adversarial attacks, but prior works have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language capabilities, new vulnerabilities have emerged. However, these multimodal targeted attacks aim to completely change the model's output to what the adversary wants. In many realistic scenarios, an adversary might seek to make only subtle modifications to the output, so that the changes go unnoticed by downstream models or even by humans. We introduce Hiding-in-Plain-Sight (HiPS) attacks, a novel class of adversarial attacks that subtly modifies model predictions by selectively concealing target object(s), as if the target object was absent from the scene. We propose two HiPS attack variants, HiPS-cls and HiPS-cap, and demonstrate their effectiveness in transferring to downstream image captioning models, such as CLIP-Cap, for targeted object removal from image captions.

Daw, Arka [ORNL] (ORCID:0009000633191271)↗
DOE OSTI2025

Performance Evaluation of Vertical Federated Machine Learning Against Adversarial Threats on Wide-Area Control System: Preprint

Federated machine learning (FL) is gaining significant popularity to develop cybersecurity solutions in power grids because of its advanced capability to support decentralized data handing at local devices, its privacy preservation, and its low-bandwidth requirement. However, the evolving adversarial machine learning (AML) threats raise significant concerns for the cybersecurity of FL architectures. The FL-based split neural network (SplitNN) achieves high performance through the decentralized training of local neural network models while preserving data privacy across multiple entities. In this paper, we propose a methodology for evaluating the performance of a vertical FLbased anomaly detector against different types of AML attacks, including denial-of-service attacks, adversarial data injection attacks, and replay attacks on the trained local models deployed in the grid network. For a case study, we consider the modified IEEE 13-bus system, and we develop SplitNN-based binary and multiclass classification models to detect, locate, and identify different types of data integrity attacks on the volt-watt control with two pooling layers: maximum pooling and AvgPool. Our experimental results, computed through performance metrics, reveal that the severity of these AML attacks varies with the integrated pooling mechanism, the type of classification model, and the nature of the cyberattack. Further, the AML attacks negatively impacted the prediction time per sample for the pretrained SplitNN during the online testing.

adversarial threats↗
DOE OSTI2024

Universal Fourier Attack for Time Series

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering defenses. We demonstrate the effectiveness of the attack on two different classification tasks through both digital and real world experiments, and show that the attack is robust against common transform-and-compare defense pipelines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Universal Fourier Attack for Time Series

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real-world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real-world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering. We demonstrate the effectiveness of the attack in two different domains, speech recognition and unintended radiated emission, and show that the attack is robust against common transform-and-compare defense pipelines.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Microreactor Security-by-Design Recommendations for Domestic and International Deployments

This report outlines methods vendors can use to incorporate security-by-design (SeBD) into their microreactor facility design to support and address security for both U.S. and international deployment. The team developed a hypothetical below-grade microreactor with a physical protection system (PPS) to protect the microreactor against acts of theft and sabotage and evaluated it against two adversary attack scenarios defined by a group of adversary subject matter experts (SMEs). The hypothetical microreactor facility consists of two distinct buildings. The first is the above-grade protected area (PA) entry control point (ECP) building, which houses security personnel responsible for conducting screenings and managing access to the PA. The second building is the reactor building, which features both an above-grade floor and a below-grade floor.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Hybrid Attack Graph Generation with Graph Convolutional Deep-Q Learning

Critical infrastructures such as power grids have become increasingly complex, connected, and vulnerable to adverse scenarios, including cyber and physical attacks and faults. Effective risk mitigation for such cyber-physical energy systems (CPES), requires preemptive knowledge of likely adversarial attack scenarios. Hybrid Attack Graph (HAG) is a structured way to represent an adversarial scenario as an attack sequence using a threat model. However, the scarcity of documented attack sequences hinders analysts and CPES planners’ ability to identify credible attack scenarios for a given CPES. We propose a data-driven Graph Convolutional Deep-Q Network (GCDQ) to address this data challenge through generating HAGs. By leveraging limited real-world observations from the MITRE ATT&CK knowledge base, our GCDQ model synthesizes realistic graphs with the targeted attribute of minimum detectability via reinforcement learning. This generative model is the first step in creating a tool to substantially boost the attack sequence dataset and enhance the performance of CPS defense-related tasks by providing insights into likely attack sequences with given attributes.

deep learning, artificial intelligence↗
DOE OSTI2021

Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition

In this article, we propose a simple yet effective approach, called point adversarial self mining (PASM), to improve the recognition accuracy in facial expression recognition (FER). Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. Here, the adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for FER.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Gumby: Quantifying multi-modal model resiliency

With the rise of cheap data and sensors, more use cases are emerging for multi-input models. Research has shown that including multiple data modalities can improve performance, suggesting that deep learning models can successfully learn to leverage complementary information from different modalities. However, this improved predictive power comes with unanticipated costs: additional inputs change model resiliency and expand the threat space for adversarial attacks. We first provide theoretical underpinnings for how adversarial success scales with input dimension. We then characterize the performance of a suite of multispectral deep learning models with different fusion approaches, quantify their relative reliance on different input bands, and evaluate their robustness to naturalistic and adversarial image corruptions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Exploring Robust Features for Improving Adversarial Robustness

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this article, we strive to explore the robust features that are not affected by the adversarial perturbations, that is, invariant to the clean image and its adversarial examples (AEs), to improve the model’s adversarial robustness. Specifically, we propose a feature disentanglement model to segregate the robust features from nonrobust features and domain-specific features. Here, the extensive experiments on five widely used datasets with different attacks demonstrate that robust features obtained from our model improve the model’s adversarial robustness compared to the state-of-the-art approaches. Moreover, the trained domain discriminator is able to identify the domain-specific features from the clean images and AEs almost perfectly. This enables AE detection without incurring additional computational costs. With that, we can also specify different classifiers for clean images and AEs, thereby avoiding any drop in clean image accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Quantum-inspired weight-constrained neural network: Reducing variable numbers by 100× compared to standard neural networks

Although quantum machine learning has shown great promise, the practical application of quantum computers remains constrained in the noisy intermediate-scale quantum era. To take advantage of quantum machine learning, we investigate the underlying mathematical principles of these quantum models and find that the quantum neural network with amplitude encoding is equivalent to a weight-constrained neural network. Motivated by this discovery, we develop a classical weight-constrained neural network. We find that this approach can reduce the number of variables in a classical neural network by a factor of 135 while preserving its accuracy. In addition, we develop a dropout method to enhance the robustness of quantum machine learning models, which are highly susceptible to adversarial attacks. This technique can also be applied to improve the adversarial robustness of the classical weight-constrained neural network, which is essential for industry applications, such as self-driving vehicles. Our work offers an approach to reduce the complexity of large classical neural networks, addressing a critical challenge in machine learning.

quantum algorithms & computation↗