Research
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.

169,051 papers · 148 categories

Trend · papers per month

24487195 · Jun 202019922001200920172026
48 results for Imperceptible Perturbations

This paper creates imperceptible, effective audio adversarial examples for speech recognition.

problem Current adversarial examples in speech recognition are easily detectable and ineffective in real-world settings.
method Developed imperceptible audio adversarial examples using psychoacoustic masking and simulated environmental distortions.
result Successfully created imperceptible, targeted adversarial examples for speech recognition that are effective in real-world settings.

Localized uncertainty attacks target uncertain regions to create imperceptible adversarial examples.

problem Adversarial examples that are imperceptible to humans and strong under deterministic classifiers.
method Localized uncertainty attacks by perturbing uncertain regions, using predictive uncertainty or surrogate models.
result Localized uncertainty attacks produce strong adversarial examples that retain input similarity.

CapsAttacks study imperceptible adversarial attacks on Capsule Networks, showing they can fool these networks.

problem Vulnerability of Capsule Networks to imperceptible adversarial attacks.
method Proposed a greedy algorithm for generating targeted imperceptible adversarial examples.
result Capsule Networks can be fooled by imperceptible adversarial attacks, similar to CNNs.

Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to a human. In this work, we propose to aug…

2017-02-14abs ↗pdf ↗

Paper defends against adversarial videos by detecting and reducing imperceptible perturbations.

problem Adversarial videos can fool well-trained video classification models.
method Temporal consistency between frames and spatial denoising to detect and reduce perturbations.
result The proposed method significantly improves robustness against adversarial attacks.

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 …

2018-06-19abs ↗pdf ↗

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic…

2017-03-03abs ↗pdf ↗

Study on adversarial training's impact on deep neural reinforcement learning policies.

problem Vulnerability of deep neural reinforcement learning policies to imperceptible adversarial perturbations.
method Two parallel approaches: Fourier spectrum analysis and feature sensitivity measurement.
result Adversarially trained policies are more sensitive to low frequency perturbations.

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art …

2016-10-26abs ↗pdf ↗

SEP uses checkpoints to protect data from training good models.

problem Protecting data from competitors training high-performance models.
method Forming perturbed examples using model checkpoints' gradients to ensure they are always unrecognized.
result SEP significantly reduces model accuracy when trained on perturbed data, demonstrating its effectiveness.

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…

2018-02-23abs ↗pdf ↗

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the system while being quasi-imperceptible for humans. More severely, there even exi…

2017-04-19abs ↗pdf ↗

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete picture of uncertainty. We therefore use principled Bayesian methods to capture…

2017-11-22abs ↗pdf ↗

We find ways to make physical signals misclassified by computer vision models.

problem Vulnerability of signal classifiers to adversarial perturbations in physical signals.
method Solving PDE-constrained optimization problems to construct imperceptible perturbations.
result Effective and physically realizable adversarial perturbations can be computed for machine learning models.

New approach to adversarial robustness with non-uniform perturbations.

problem Real-world adversaries craft adversarial examples with non-uniform perturbations.
method Proposes non-uniform perturbations based on feature dependencies and data distribution.
result Shows improved robustness to real-world attacks compared to uniform perturbations.

Improved algorithm speeds up generation of universal adversarial perturbations.

problem Slow generation of universal adversarial perturbations.
method Optimized algorithm based on orientation of perturbation vectors.
result Significantly faster generation of universal perturbations with higher fooling rates.

This paper analyzes ββ-Variational Classifiers for robustness and adversarial perturbation detection.

problem Limited robustness of deep neural networks in predictions.
method An analysis of ββ-Variational Classifiers, focusing on their robustness and adversarial perturbation detection.
result Novel insights into the generative component of ββ-Variational Classifiers.

Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack either. Most of adversarial attack methods are focused on success rate or perturbations size, while we a…

2018-12-01abs ↗pdf ↗

Develops new methods to create imperceptible image changes that fool classifiers.

problem Improving the robustness of image classifiers by creating subtle changes undetectable to humans.
method Two methods: Edge-Aware and Color-Aware, designed to reduce detectability of image perturbations.
result Demonstrated that the new methods effectively cause misclassification and are computationally efficient.

DIP-FAT improves adversarial training by diversifying perturbations.

problem Adversarial examples fool deep neural networks, leading to overfitting and poor performance.
method DIP-FAT uses random directions to diversify perturbations in adversarial training.
result DIP-FAT reduces overfitting and improves clean data accuracy.

New approach makes adversarial examples less suspicious without changing perceptual salience.

problem Robustness of deep neural networks to unsuspicious adversarial examples.
method Splitting images into foreground and background, allowing larger perturbations in background while maintaining low cognitive salience.
result Dual-perturbation attacks are effective against classifiers robust to conventional attacks and adversarial training yields more robust classifiers.

Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.

problem Susceptibility of audio classifiers to adversarial attacks on spectrograms.
method Applying adversarial attacks to spectrograms and reconstructing audio waveforms.
result Perturbed spectrograms can fool 2D CNNs and 1D CNNs trained on audio waveforms.

Adversarial weight perturbations can inject backdoors into trained neural models.

problem Security risk of using publicly available trained models due to backdoors.
method Extended adversarial perturbations to model weights, using a composite loss and projected gradient descent.
result Adversarial weight perturbations can be successfully injected with very small changes, exposing security risks across various tasks.

AdversarialPSO uses fewer queries to create high-success-rate adversarial examples.

problem Creating imperceptible adversarial examples with high success rates in black-box settings.
method AdversarialPSO, a black-box attack using Particle Swarm Optimization.
result Achieved high success rates (99.6% on CIFAR-10, 96.3% on MNIST, 82.0% on Imagenet) with fewer queries.

Linear classifiers can be made robust to strong adversarial examples attacks.

problem Understanding and quantifying adversarial examples in linear classification.
method Proposed a more practical definition of strong adversarial examples, showing robustness to attacks.
result Linear classifiers can be made robust to strong adversarial examples attacks.

Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers …

2018-03-21abs ↗pdf ↗

Classifiers fail to classify correctly input images that have been purposefully and imperceptibly perturbed to cause misclassification. This susceptability has been shown to be consistent across classifiers, regardless of their type, architecture or parameters. Common defenses against adversarial attacks modify the cla…

2018-12-08abs ↗pdf ↗

TensorShield defends images from adversarial attacks using tensor decomposition.

problem Adversarial attacks on images can fool deep neural networks.
method Tensor decomposition to find low-rank approximations of images, reducing high-frequency perturbations.
result TensorShield outperforms existing methods like SLQ by 14% against FGSM attacks.

The susceptibility of deep learning to adversarial attack can be understood in the framework of the Renormalisation Group (RG) and the vulnerability of a specific network may be diagnosed provided the weights in each layer are known. An adversary with access to the inputs and outputs could train a second network to clo…

2018-03-29abs ↗pdf ↗