Search NASA⌕ Search

SEARCH · Search NASA

Results for “adversarial robustness”

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 OSTI2021

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations

We report while existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations --- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Adversarial classification via distributional robustness with Wasserstein ambiguity

Abstract We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. Numerical experiments show that, despite the nonconvexity of this formulation, standard descent methods appear to converge to the global minimizer for this problem. Inspired by this observation, we show that, for a certain class of distributions, the only stationary point of the regularized ramp loss minimization problem is the global minimizer.

Ho-Nguyen, Nam (ORCID:0000000344647730)↗
DOE OSTI2023

SwitchX : Gmin-Gmax Switching for Energy-efficient and Robust Implementation of Binarized Neural Networks on ReRAM Xbars

Memristive crossbars can efficiently implement Binarized Neural Networks (BNNs) wherein the weights are stored in high-resistance states (HRS) and low-resistance states (LRS) of the synapses. We propose SwitchX mapping of BNN weights onto ReRAM crossbars such that the impact of crossbar non-idealities, that lead to degradation in computational accuracy, are minimized. Essentially, SwitchX maps the binary weights in such a manner that a crossbar instance comprises of more HRS than LRS synapses. We find BNNs mapped onto crossbars with SwitchX to exhibit better robustness against adversarial attacks than the standard crossbar mapped BNNs, the baseline. Finally, we combine SwitchX with state-aware training (that further increases the feasibility of HRS states during weight mapping) to boost the robustness of a BNN on hardware. We find that this approach yields stronger defense against adversarial attacks than adversarial training, a state-of the-art software defense. We perform experiments on a VGG16 BNN with benchmark datasets (CIFAR-10, CIFAR-100 and TinyImagenet) and use Fast Gradient Sign Method (ϵ = 0.05 to 0.3) and Projected Gradient Descent (ϵ = $\frac{2}{255}$ to $\frac{32}{255}$, α = $\frac{2}{255}$) adversarial attacks. We show that SwitchX combined with state-aware training can yield upto ~35% improvements in clean accuracy and ~6–16% in adversarial accuracies against conventional BNNs. Furthermore, an important by-product of SwitchX mapping is increased crossbar power savings, owing to an increased proportion of HRS synapses, which is furthered with state-aware training. We obtain upto ~21–22% savings in crossbar power consumption for state-aware trained BNN mapped via SwitchX on 16 × 16 and 32 × 32 crossbars using the CIFAR-10 and CIFAR-100 datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Robust Explanations using Diverse Adversarially Trained Ensembles, Multi-Modal Contrastive Learning, and Attribution-based Confidence Metrics

The primary objective of this project is to strengthen the trustworthiness of AI systems by designing algorithms that make their internal decision-making processes more understandable to human users. This involves creating clear, interpretable explanations for AI decisions and developing metrics to assess these explanations' validity and reliability. Significant progress has been achieved through (i) developing symbolic explanations, (ii) generating meaningful interpretive insights, (iii) establishing accuracy and confidence metrics, and (iv) devising methods to evaluate the knowledge boundaries of AI models. To date, the research findings have been shared in peer-reviewed publications, with accompanying scientific and technical information (STI) detailed below.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2024

Double Visual Defense

This is the official code for the paper "Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness". This code can be used to produce vision language models (VLMs), like LLaVA, with enhanced robustness to adversarial attacks (e.g. jailbreaks).

Bartoldson, Brian [Lawrence Livermore National Lab↗
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 OSTI2023

Robust Resilient Signal Reconstruction under Adversarial Attacks

We consider the problem of signal reconstruction for a system under sparse signal corruption by a malicious agent. The reconstruction problem follows the standard error coding problem that has been studied extensively in the literature. We include a new challenge of robust estimation of the attack support. The problem is then cast as a constrained optimization problem merging promising techniques in the area of deep learning and estimation theory. A pruning algorithm is developed to reduce the "false positive" uncertainty of data-driven attack localization results, thereby improving the probability of correct signal reconstruction. Sufficient conditions for the correct reconstruction and the associated reconstruction error bounds are obtained for both exact and inexact attack support estimation. Moreover, a simulation of a water distribution system is presented to validate the proposed techniques.

Robust, Signal reconstruction, Resilient estimator↗
DOE OSTI2025

Exploring Black-box Adversarial Attacks on Low-rank Constrained Neural Networks

Low-rank compression has been shown as an effective tool to reduce parameter counts of convolutional and vision transformer architectures; however, low-rank training often reduces model robustness to adversarial perturbations. In this work, we explore the effects of low-rank training on black-box attacks, where attacked images are generated without knowledge of the low-rank parameters. We find that low-rank training is not sufficient as a black-box defense and can sometimes produce worse than expected as compared to baseline models. Influencing the spectrum of the low-rank models during training, which is known to increase model robustness against white-box attacks, improves black-box performance as well.

Schnake, Stefan [ORNL] (ORCID:0000000215183538)↗
DOE OSTI2023

Robust Power System Stability Assessment Against Adversarial Machine Learning-Based Cyberattacks via Online Purification

The increasing complexity associated with renewable generation brings more challenges to power system stability assessment (SA). Data-driven approaches based on machine learning (ML) techniques for stability assessment have received significant research interest and shown their promising performance. However, ML-based models are recognized to be vulnerable to adversarial disturbances, where a slight perturbation to power system measurements could lead to unacceptable errors. To address this issue, this paper develops a novel lightweight mitigation strategy, i.e., robust online stability assessment (ROSA), to enhance the ML-based assessment model against both white-box and the black-box adversarial disturbances (i.e., purification) in the online implementation. The ROSA involves a supervised learning-based module for the primary stability assessment and a self-supervised learning-based module. Further, the two modules are trained jointly with different objective (loss) functions and implemented in sequence. A suitable purification objective and various time-series data augmentation methods are designed for SA applications to tackle adversarial disturbances adaptively. Case studies are performed, and the comparative results have clearly illustrated the competitive, robust accuracy against various adversarial scenarios and verified the effectiveness of the proposed online purification strategy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Noise Robustness and Experimental Demonstration of a Quantum Generative Adversarial Network for Continuous Distributions

Abstract The potential advantage of machine learning in quantum computers is a topic of intense discussion in the literature. Theoretical, numerical, and experimental explorations will most likely be required to understand its power. There have been different algorithms proposed to exploit the probabilistic nature of variational quantum circuits for generative modeling. In this paper, a hybrid architecture for quantum generative adversarial networks (QGANs) is employed and their robustness in the presence of noise is studied. A simple way of adding different types of noise to the quantum generator circuit is devised, and the noisy hybrid QGANs (HQGANs) are simulated numerically to learn continuous probability distributions, and to show that the performance of HQGANs remains unaffected. The effect of different parameters on the training time is also investigated to reduce the computational scaling of the algorithm and simplify its deployment on a quantum computer. The training on Rigetti's Aspen‐4‐2Q‐A quantum processing unit is then performed, and the results from the training are presented. The authors' results pave the way for experimental exploration of different quantum machine learning algorithms on noisy intermediate‐scale quantum devices.

Anand, Abhinav↗
DOE OSTI2021

Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that this vulnerability arises, in part, because neural network classifiers rely on highly predictive but brittle “non-robust” features. In this paper we extend the work of Ilyas et al. by investigating the nature of the input patterns that give rise to these features. In particular, we hypothesize that in a neural network trained in a standard way, non-robust features respond to small, “non-semantic” patterns that are typically entangled with larger, robust patterns, known to be more human-interpretable, as opposed to solely responding to statistical artifacts in a dataset. Thus, adversarial examples can be formed via minimal perturbations to these small, entangled patterns. In addition, we demonstrate a corollary of our hypothesis: robust classifiers are more effective than standard (non-robust) ones as a source for generating transferable adversarial examples in both the untargeted and targeted settings. The results we present in this paper provide new insight into the nature of the non-robust features responsible for adversarial vulnerability of neural network classifiers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Robust Assessment of Real-World Adversarial Examples

We explore rigorous, systematic, and controlled experimental evaluation of adversarial examples in the real world and propose a testing regimen for evaluation of real world adversarial objects. We show that for small scene/ environmental perturbations, large adversarial performance differences exist. Current state of adversarial reporting exists largely as a frequency count over a dynamic collections of scenes. Our work underscores the need for either a more complete report or a score that incorporates scene changes and baseline performance for models and environments tested by adversarial developers. We put forth a score that attempts to address the above issues in a straight-forward exemplar application for multiple generated adversary examples. We contribute the following: 1. a testbed for adversarial assessment, 2. a score for adversarial examples, and 3. a collection of additional evaluations on testbed data.

deep learning, adversarial machine learning, machi↗
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 OSTI2021

Transfer Learning using Denoising Auto-Encoders for Cellular-Level Annotation of Tumor in Pathology Slides

Adversarial examples can produce altered classifications using only seemingly innocuous, imperceptible perturbations to the original image. The imperceptibility of adversarial perturbations suggests that the corresponding classifiers use decision criteria different than those of a human. In a medical setting, inexplicable decision criteria confound a pathologist’s willingness to trust machine-generated annotations. Here, we analyze denoising tumor detection models to see if they are robust to imperceptible adversarial perturbations. Moreover, to be more fully trusted by pathologists, we require tumor detectors that generate interpretable annotations which segment pathology slides into tumorous and normal regions at the cellular level. We therefore compare transfer learning based on two different autoencoder architectures, one derived from a deep denoising bottleneck autoencoder and one from an over-complete sparse autoencoder. Both autoencoders were first trained in an unsupervised manner on a set of pathology slides drawn from the Camelyon16 dataset. The latent representations produced by each autoencoder were then passed to separate neural networks that were trained in a supervised manner on binary tumor-normal masks generated by pathologists at cellular resolution. Both tumor detectors supported better than 90% AUC PR as measured by the area under the precision/recall curve on a held-out pathology slide. To assess the underlying decision criteria used by both tumor detectors, we constructed imperceptible adversarial examples which reduced the AUC PR of both models to less than 70%. Random noise of the same amplitude had almost no effect on the AUC PR of either model. Additionally, each tumor detector was resistant to adversarial “transfer” attacks targeting the other. The adversarial perturbations showed strong characteristic differences: the deep denoising models perturbations were a very diffuse, seemingly unrecognizable pattern while the sparse coding models perturbations showed traces of tissue cells.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Generative $β$-hairpin design using a residue-based physicochemical property landscape

De novo peptide design is a new frontier that has broad application potential in the biological and biomedical fields. Most existing models for de novo peptide design are largely based on sequence homology that can be restricted based on evolutionarily derived protein sequences and lack the physicochemical context essential in protein folding. Generative machine learning for de novo peptide design is a promising way to synthesize theoretical data that are based on, but unique from, the observable universe. In this study, we created and tested a custom peptide generative adversarial network intended to design peptide sequences that can fold into the -hairpin secondary structure. This deep neural network model is designed to establish a preliminary foundation of the generative approach based on physicochemical and conformational properties of 20 canonical amino acids, for example, hydrophobicity and residue volume, using extant structure-specific sequence data from the PDB. The beta generative adversarial network model robustly distinguishes secondary structures of hairpin from α helix and intrinsically disordered peptides with an accuracy of up to 96% and generates artificial -hairpin peptide sequences with minimum sequence identities around 31% and 50% when compared against the current NCBI PDB and nonredundant databases, respectively. These results highlight the potential of generative models specifically anchored by physicochemical and conformational property features of amino acids to expand the sequence-to-structure landscape of proteins beyond evolutionary limits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Optimization-Based Resiliency Verification in Microgrids via Maximal Adversarial Set Characterization

Critical energy infrastructures are increasingly relying on advanced sensing and control technologies for efficient and optimal utilization of flexible energy resources. Algorithmic procedures are needed to ensure that such systems are designed to be resilient to a wide range of cyber-physical adversarial events. This paper provides a robust optimization framework to quantify the largest adversarial perturbation that a system can accommodate without violating pre-specified resiliency metrics. We formulate the maximal adversarial set characterization as a bi-level optimization problem which is solved via Lagrangian relaxations.We illustrate the proposed algorithm on an islanded microgrid example: a modified IEEE 123-node feeder with distributed energy resources. Simulations are carried out to characterize the tolerable adversarial perturbations for varying levels of available flexibility (energy reserves).

Nazir, Mohammad Nawaf↗