This work explores how neural architecture search can improve adversarial robustness without adversarial training.
problem Improving adversarial robustness of neural networks without adversarial training.
method Experimented with hand-crafted and NAS-based architectures to compare robustness to PGD attacks.
result NAS-based architectures are more robust for small-scale attacks, but hand-crafted architectures are more robust for larger datasets and tasks.
RobNets improve robustness of deep neural networks against adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method One-shot neural architecture search, finetuning sub-networks, and analyzing robustness indicators.
result RobNets achieve superior robustness performance across various datasets.
This paper investigates how network width and depth affect adversarially robust DNNs.
problem Understanding architectural configurations for adversarially robust DNNs.
method Comprehensive investigation on the impact of network width and depth on adversarial robustness.
result Optimal architectural configuration for adversarial robustness exists and can improve robustness.
This work explores how neural network architecture affects robustness to noisy labels.
problem The impact of neural network architecture on robustness to noisy labels.
method Formal framework connecting robustness to architecture alignments, measured by predictive power in representations.
result Network robustness to noisy labels improves when its architecture is more aligned with the target function.
This work benchmarks and theorizes robust NAS under adversarial training.
problem Lack of benchmark evaluations and theoretical guarantees for robust NAS architectures under adversarial training.
method Released a comprehensive data set and established a generalization theory using the neural tangent kernel.
result Established a generalization theory for robust NAS architectures under adversarial training.
The paper analyzes different neural network architectures for 3D point cloud processing.
problem Understanding the effects of specific intermediate-layer network architectures on 3D point cloud processing.
method Designing five metrics to diagnose various types of DNNs and conducting comparative studies.
result The hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs are verified.
Paper evaluates robustness of NAS against poisoning attacks.
problem Robustness of Neural Architecture Search (NAS) against poisoning attacks.
method Evaluation of Efficient NAS (ENAS) against carefully designed ineffective operations in poisoning attacks.
result Demonstrates how poisoning attacks exploit design flaws in ENAS controller.
New method creates diverse neural ensembles for better uncertainty estimation and robustness.
problem Creating more robust neural networks for uncertainty estimation and dataset shift.
method Automatically constructing ensembles with varying architectures.
result Ensembles with varying architectures outperform deep ensembles in accuracy, uncertainty calibration, and robustness.
Sensor fusion is a key technology that integrates various sensory inputs to allow for robust decision making in many applications such as autonomous driving and robot control. Deep neural networks have been adopted for sensor fusion in a body of recent studies. Among these, the so-called netgated architecture was propo…
Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous Advantage Actor-Critic (A3C) algorithm where the total input dimensionality is halv…
Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are often affected by distortions that not accounted for by the training datasets. In…
Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper, we propose a novel deep learning-based multimodal fusion architecture for class…
New theory explains how noisy, high-dimensional data can still lead to robust predictions.
problem Modern machine learning models achieve high performance with noisy, high-dimensional data.
method Synthesizes principles from Information Theory, Latent Factor Models, and Psychometrics to clarify predictive robustness.
result Predictive robustness arises from data architecture and model capacity, not just data cleanliness.
Proposes DMOC for more nuanced neural network robustness.
problem Lipschitz continuity is too coarse for nuanced data-dependent behavior.
method Data-driven, architecture-agnostic framework based on DMOC.
result DMOC provides a finer notion of robustness relative to data distribution.
Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high-level features and end-to-end sensor fusion solutions, existing deep learning based sensor fusion techniques including deep gating architec…
We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustness for a given architecture, and provide theoretical insight into the trade-off. Specifically we in…
VQC-MLPNet combines quantum and classical elements for scalable quantum machine learning.
problem Challenges in expressivity, trainability, and noise resilience of VQCs.
method Hybrid architecture with a VQC generating weights for a classical MLP during training.
result Improved expressivity, trainability, and robustness compared to standalone quantum or hybrid approaches.
Enhances GNN robustness during inference using Conditional Random Fields.
problem Vulnerability of GNNs to adversarial attacks.
method Post-hoc approach using Conditional Random Fields (CRF).
result Improves robustness of GNNs across various models.
BagCert efficiently certifies robustness against adversarial patches on image classifiers.
problem Adversarial patches pose a threat to autonomous systems' perception component.
method BagCert combines model architecture and certification procedure for efficient inference.
result BagCert certifies 10,000 examples in 43 seconds on a single GPU, achieving 86% clean and 60% certified accuracy against 5x5 patches.
New deep learning models inspired by fuzzy logic are more robust to adversarial attacks.
problem Flawed generalization in deep neural networks leading to adversarial examples.
method Inspired by fuzzy logic, new architectures combining alternative design elements.
result New models are more robust to adversarial examples and noise.
New robustness measure accounts for task-specific symmetries.
problem Traditional robustness measures fail for tasks with inherent symmetries.
method Sound notion of adversarial robustness for equivariant tasks, using randomized smoothing and graph edit distance certificates.
result Provable robustness can be achieved for various tasks with inherent symmetries.
Paper examines Go AI robustness against adversarial attacks.
problem Superhuman Go AIs are vulnerable to simple adversarial strategies.
method Three defenses tested: adversarial training, iterated adversarial training, and changing network architecture.
result No defense is robust against newly trained adversaries, and attacks are similar to cyclic attacks.
It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the fact that neural networks operate on high dimensional data, they overfit, or they are too linear. H…
High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is to automate a part of tuning process. Aiming at a fast, robust, and widely-appli…
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adv…
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
problem Robust 3D point cloud classification under corruption.
method Mapper algorithm for structural decomposition, GIN for graph classification.
result Mapper-GIN achieves competitive accuracy with minimal parameters.
Novel neural network approximates exact distance for robust classification.
problem Adversarial attacks on neural networks in safety-critical systems.
method Signed Distance Classifiers (SDCs) and Unitary-Gradient Neural Network.
result Approximates exact distance from classification boundary for certifiable predictions.
We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU). We prove that our architecture exhibits robustness to the input perturbation: the output feature of the neural network exhibits a Lipschitz continuity in terms of the input perturbation. We fu…
PhysicsNAS generalizes PBL by integrating NAS into neural networks with physical priors.
problem Leveraging physical priors for robust inference in machine learning.
method Physics-based neural architecture search (PhysicsNAS) integrating physical priors and neural networks.
result PhysicsNAS is a top-performer across various physical models and dataset qualities.
New Transformers maintain Lipschitz continuity for robustness.
problem Ensuring robustness in Transformers for safety-sensitive applications.
method Introducing gradient-descent-type in-context Transformers with explicit Euler steps of negative gradient flows.
result Universal approximation theorem for Lipschitz continuous Transformers.
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
problem Estimating parameters of a mechanical vehicle model from noisy acceleration data.
method Introduced a convolutional neural network with two objective functions: naive and hybrid.
result The hybrid objective function outperforms the naive one in robustness on noisy input data.
Paper improves deep learning models for limit order book data.
problem Deep learning models' performance depends on robust input data representation.
method Identified and modified flaws in existing representations.
result Proposed modifications lead to state-of-the-art performance.
TGCN learns from multi-relational graphs, improving SSL performance.
problem Scalable semi-supervised learning from multi-relational data.
method Tensor-graph convolutional network with dynamic weights and graph-based regularizers.
result Significantly improved SSL performance over standard GCNs.
Neural nets learn robust geometric data representations.
problem Ensuring neural networks are robust to adversarial attacks.
method Topological Data Analysis via persistence diagrams, Lipschitz stability.
result Certified ε-robustness on ORBIT5K dataset. A new machine learning model uses matrix exponentials for universal approximation.
problem Developing a robust and efficient machine learning model.
method Introduces a novel architecture using matrix exponentials as the only nonlinearity.
result The model achieves universal approximation properties and outperforms other models on benchmark tasks.
Study shows how bias in optimization affects robustness in adversarial settings.
problem Understanding and mitigating implicit bias in adversarially robust models.
method Analyzes the implicit bias in robust empirical risk minimization and its impact on generalization.
result Implicit bias in optimization can significantly affect robust generalization.
This work studies adversarial transferability and proposes ensemble methods to improve robustness.
problem Adversarial transferability in neural networks and its implications for robustness.
method Investigates the effect of various factors on adversarial transferability and proposes ensemble attack methods.
result Transferability is significantly hampered by input quantization and architectural mismatch, but not by initialization.
SPLASH units improve deep neural network accuracy and adversarial robustness.
problem Improving deep neural network accuracy and adversarial robustness.
method SPLASH units are learnable activation functions with specific properties that enhance both accuracy and robustness.
result SPLASH units significantly increase adversarial robustness of deep neural networks.
AMF-VI uses adaptive mixtures of flows for robust VI across diverse distributions.
problem Inconsistent behavior of single-flow models across different distributions.
method Sequential expert training of individual flows and adaptive global weight estimation via likelihood-driven updates.
result AMF-VI achieves lower negative log-likelihood and stable gains in transport metrics across various posterior families.
Study makes code models robust to small changes that keep functionality.
problem Vulnerability of deep neural networks to adversarial examples in source code.
method Defined a powerful adversary and adversarial training to learn robust models.
result Significant gains in robustness demonstrated across different languages and architectures.
LOT improves adversarial robustness by training 1-Lipschitz convolution layers.
problem Improving adversarial robustness of deep neural networks.
method LOT: Layer-wise Orthogonal Training for 1-Lipschitz convolution layers.
result LOT significantly enhances certified robustness of Lipschitz-bounded models.
In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular networks with a learnt structure can generalise better on small datasets, while f…
Transformers can be hijacked by context, but deeper models are more robust.
problem Robustness of Transformers against context hijacking for linear classification.
method Developed a theoretical analysis on the robustness of linear transformers, considering model depth, training context lengths, and number of hijacking context tokens.
result Deeper transformers are more robust to context hijacking.
Overparametrized models are vulnerable to adversarial perturbations, affecting robust generalization.
problem Understanding how overparametrization impacts robustness in adversarial training.
method Analyzing random features regression models with a precise asymptotic formula.
result High overparametrization can hurt robust generalization in adversarially trained models.
This paper explores BDL hyperparameters for robust polynomial mapping with noise.
problem Designing BDL hyperparameters for robust function mapping with uncertainty quantification.
method Mapping Bayesian connectionist representations to polynomials of varying orders and noise types.
result Optimal network depth and ensemble size for prediction and uncertainty quantification.
DARTS- improves robustness by factoring out skip connections' advantage.
problem Performance collapse in DARTS architecture search.
method Factor out skip connections' advantage with an auxiliary skip connection.
result Significantly improved robustness across various datasets.
Transformers are less sensitive to input perturbations compared to other models.
problem Understanding the inductive biases of transformers and distinguishing them from other architectures.
method Identified token-wise sensitivity as a metric to explain transformers' inductive biases across different data modalities.
result Transformers have lower sensitivity than MLPs, CNNs, ConvMixers, and LSTMs, across vision and language tasks.
A multilayer perceptron can behave as a generative classifier by applying bidirectional learning (BL). It consists of training an undirected neural network to map input to output and vice-versa; therefore it can produce a classifier in one direction, and a generator in the opposite direction for the same data. The lear…