Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications. In this paper, we conjecture that the leading cause of adversarial vulnerabili…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Adversarial vulnerability”
New method certifies joint adversarial robustness of model ensembles.
problem Ensuring robustness of model ensembles against adversarial attacks.
method Proposes a novel technique to certify joint robustness, building on prior work on single-model robustness certification.
result Demonstrates the effectiveness of certifying joint robustness of ensembles, improving understanding of ensemble defenses.
Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.
problem Understanding the vulnerability of high-dimensional linear classifiers to adversarial attacks.
method Introducing a new error metric to quantify model vulnerability, and rigorously characterizing these metrics in asymptotic settings.
result As models become more overparameterized, their vulnerability to label-preserving perturbations increases.
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisi…
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications:…
Study reveals how neural network smoothness affects their vulnerability to adversarial attacks.
problem Understanding adversarial vulnerability in deep learning networks.
method Analysis of manifold smoothness and generalization capability of deep neural networks trained with local errors.
result High generalization accuracy requires a fast power-law decay of eigen-spectrum of hidden representations.
This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adversarial attacks than other neural networks. However, our experiments show that capsule networks can be fooled as easily as convolutional neur…
Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
New normalization method makes neural networks more robust to adversarial attacks.
problem Adversarial vulnerability of BatchNorm in deep neural networks.
method Identified distribution shift caused by adversarial images, proposed RobustNorm to use inference-time statistics.
result RobustNorm makes models more robust to adversarial attacks without sacrificing BatchNorm benefits.
Optimal adversarial attacks minimize mutual information, revealing classifier vulnerabilities.
problem Designing optimal attacks to degrade machine learning performance.
method Information-theoretic approach to finding optimal perturbations.
result Optimal attacks minimize mutual information between degraded and original signals.
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially train…
This work examines how adversarial vulnerability changes with the dimensionality of the subspace of perturbations.
problem Understanding adversarial vulnerability in constrained input spaces.
method Investigates adversarial vulnerability in subspace of the input space with varying dimensions, using PGD attacks and analyzing the dependence on and .
result Adversarial success of PGD attacks is a monotonically increasing function of $ε( rac{dim(V)}{dim(X)})^{ rac{1}{q}}$.
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models more vulnerable---is surprisingly easy. After presenting some proofs of concept on MNIST, we introduce a generic tilting attack that injects …
Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information geometry, we provide a reasonable explanation for the vulnerability of deep learning models. By consi…
Deep networks can overfit benignly but still be vulnerable to adversarial attacks.
problem Adversarial vulnerability of deep neural networks trained with benign overfitting.
method Investigated causes of adversarial vulnerability, identified label noise as a key factor, and explored the impact of training procedures and representation learning.
result Adversarial robustness requires more complex decision boundaries than simple ones, suggesting the need for better representation learning.
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the…
NTK neural networks are robust to adversarial attacks in nonparametric regression.
problem Adversarial robustness of neural networks in nonparametric regression.
method Gradient flow with early stopping for NTK neural networks, proving robustness in Sobolev spaces.
result NTK neural networks achieve optimal adversarial robustness rates in Sobolev spaces.
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well a…
Deep neural networks are vulnerable to adversarial attacks.
New insights into adversarial vulnerability linked to manifold separability issues.
problem Adversarial vulnerability in machine learning models.
method Characterized data distribution as a low-dimensional manifold, focusing on on/off manifold directions and the impact of first-order vs. second-order optimization methods.
result First-order optimization methods lead to poor convergence in the off-manifold direction, causing adversarial vulnerability in inseparable datasets.
Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of -bounded and -minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properti…
Mathematical framework to understand neural network vulnerability.
problem Understanding and quantifying adversarial vulnerability in neural networks.
method Develops a geometric framework using Ricci curvature to measure decision boundaries and adversarial perturbations.
result Establishes a new theory linking adversarial attacks to Ricci curvature of decision boundaries.
Interpolating label noise makes models vulnerable to adversarial attacks.
problem Adversarial vulnerability of models trained on noisy labels.
method Theoretical analysis of label noise and adversarial risk relationship.
result Uniform label noise induces adversarial risk similar to worst-case poisoning.
This paper studies adversarial examples in NIDS, revealing their vulnerability.
problem Vulnerability of machine learning-based NIDS to adversarial examples.
method Used evolutionary computation and deep learning to generate adversarial examples.
result Adversarial examples cause high misclassification rates in various machine learning models.
New holistic approach measures sample-level adversarial vulnerability for trustworthy systems.
problem Inherent bias in adversarial attacks across subgroups.
method Combining high-frequency feature reliance and sample-distance to decision boundary.
result Holistic approach improves adversarial vulnerability estimation and system trustworthiness.
DL models for MTS regression are vulnerable to adversarial attacks, posing risks in safety-critical applications.
problem Vulnerability of DL models to adversarial examples in MTS regression.
method Adversarial attack generation techniques from image classification were adapted for MTS.
result All state-of-the-art DL regression models (CNN, LSTM, GRU) are vulnerable to adversarial attacks.
Lazy neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness issues in lazy training models.
method Extending recent work on adversarial examples to lazy training models.
result Over-parametrized neural networks that generalize well remain vulnerable to single-step gradient ascent attacks.
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to …
Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an input. There exists a large number of previous works which proposed to defend agai…
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural …
mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural Networkscs.LG
mFI-PSO generates effective adversarial images for DNNs.
problem Vulnerability of DNNs to small perturbations in images.
method Uses mFI for pixel selection and PSO for objective functions.
result mFI-PSO effectively designs flexible adversarial images.
Adversarial policies beat superhuman Go AI systems.
problem Vulnerability of superhuman AI systems to adversarial attacks.
method Training adversarial policies to trick KataGo into making blunders.
result Adversarial policies achieve >97% win rate against KataGo at superhuman settings.
Recent advancements in radio frequency machine learning (RFML) have demonstrated the use of raw in-phase and quadrature (IQ) samples for multiple spectrum sensing tasks. Yet, deep learning techniques have been shown, in other applications, to be vulnerable to adversarial machine learning (ML) techniques, which seek to …
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also reduces robustness to small adversarial input perturbations and noise by d…
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy attacks. In this work we demonstrate how model inversion attacks, extracting trai…
Recently, Convolutional Neural Networks (CNNs) demonstrate a considerable vulnerability to adversarial attacks, which can be easily misled by adversarial perturbations. With more aggressive methods proposed, adversarial attacks can be also applied to the physical world, causing practical issues to various CNN powered a…
It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing adversarial attacks, we present a new type of global adversarial attacks for assess…
Improved estimation of concentration using half-spaces for adversarial vulnerability.
problem Understanding the concentration of measure phenomenon and its impact on adversarial vulnerability.
method Extending Gaussian Isoperimetric Inequality to non-spherical Gaussian measures and arbitrary ℓ_p-norms, using half-spaces to estimate concentration.
result Proposed method finds tighter intrinsic robustness bounds, providing evidence against concentration as a cause of adversarial vulnerability.
Two-layer networks trained on low-dimensional subspaces are vulnerable to adversarial examples.
problem Vulnerability of two-layer neural networks to adversarial examples on low-dimensional subspaces.
method Analysis of gradient behavior and effect of initialization scale and regularization.
result Decreasing initialization scale or adding L2 regularization can improve robustness to adversarial perturbations orthogonal to the data.
Adversarial tweets can fool stock prediction models, causing financial loss.
problem Vulnerability of stock prediction models to adversarial attacks on social media.
method Solving combinatorial optimization problems with semantic and budget constraints to generate adversarial tweets.
result Adversarial tweets can fool stock prediction models and cause significant financial loss.
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity and invariance. We sh…
CausAdv detects adversarial examples using causal reasoning.
problem Vulnerability of CNNs to adversarial perturbations.
method Causal framework based on counterfactual reasoning.
result Adversarial examples exhibit different CI distributions compared to clean samples.
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability that captures the maximum change …
While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and sophistication of attacks, has prompted the need for a data driven solution, wit…