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

16.7%33.3%50.0%66.7% · Jul 199219922001200920182026
48 results for dominant adversarial examples

Paper tackles adversarial attacks on A3C path finding, proposing Gradient Band-based Adversarial Training.

problem Adversarial attacks on A3C path finding.
method Gradient Band-based Adversarial Training with CDG method.
result Gradient Band-based Adversarial Training achieves high attack immunity.

This paper characterizes adversarial examples in deep learning.

problem Security threats posed by adversarial attacks in deep learning systems.
method Statistical characterization of adversarial examples, easy and hard categorization of attacks, extensive experimental study.
result Adversarial attacks behave differently under different hyperparameters and frameworks.

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.

Empirical study on SGD hyperparameters and adversarial robustness.

problem Effect of SGD hyperparameters on adversarial robustness and generalization.
method Empirical observation of learning rate, batch size, and momentum effects on adversarial robustness and generalization.
result Constant learning rate to batch size ratio leads to good generalization and almost constant adversarial robustness.

Light-based attacks can misclassify images without altering physical objects.

problem Physical attacks on deep learning classifiers are limited by the ability to modify inputs directly.
method Constructs an experimental setup with a light projection source, object, and camera. Uses differential evolution to select light patterns.
result Projected light can degrade classification accuracy from 98% to 22% for 2D objects and from 89% to 43% for 3D objects.

Paper introduces a new method to create adversarial examples against gradient-obfuscating defenses.

problem Crafting adversarial examples to fool gradient-obfuscating defenses.
method Stochastic Substitute Training (SST), a gray-box approach.
result Adversaries can create adversarial examples without knowledge or limited information about the defense.

Method identifies over-optimized adversarial examples using IQR-based logit thresholding.

problem Over-optimized adversarial examples are hard to detect due to model optimization.
method IQR-based logit thresholding method for identifying over-optimized adversarial examples.
result The logits of the model are more useful in detecting over-optimized adversarial examples.

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.

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 …

2017-12-19abs ↗pdf ↗

Enhances single-step adversarial training to defend against iterative adversarial examples.

problem Defending against iterative adversarial examples in neural networks.
method Identified and leveraged empirical properties of Iter-Adv to improve Single-Adv.
result Enhanced Single-Adv to defend against iterative adversarial examples with improved accuracy and reduced training cost.

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.

Steganalysis improves detection of adversarial examples.

problem Detecting adversarial examples from deep neural networks.
method Enhancing steganalysis features by estimating adversarial attack probabilities.
result The method accurately detects adversarial examples and resists secondary attacks.

New method defends against both single-step and iterative adversarial examples.

problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.

Proposes BATer for improved adversarial example detection.

problem Detecting adversarial examples in neural networks.
method Introduces a Bayesian adversarial example detector (BATer) using random components in a Bayesian neural network.
result BATer outperforms state-of-the-art detectors in adversarial example detection.

Enhances adversarial example transferability by fine-tuning existing examples.

problem Adversarial examples are often overfit to a source model, limiting black-box transferability.
method Intermediate Level Attack (ILA) fine-tunes adversarial examples on a pre-specified layer of the source model.
result ILAs achieve high transferability to target models without knowledge of their architecture.

GanDef uses GANs to defend against adversarial examples in neural networks.

problem Defending against adversarial examples in neural networks.
method GAN-based adversarial training defense using a competition game to regulate feature selection.
result GanDef trains a classifier to defend against adversarial examples with high accuracy.

This paper explores how temporal dependency in audio data can improve robustness against adversarial examples.

problem Mitigating adversarial examples in audio data.
method Exploiting temporal dependency to gain discriminative power against audio adversarial examples.
result Temporal dependency can be used to resist adaptive attacks on audio adversarial examples.

Proposes a probabilistic method for generating semantically-aware adversarial examples.

problem Generating adversarial examples that are difficult for humans to detect while preserving semantics.
method Embeds subjective understanding of semantics as a distribution into adversarial example generation.
result Achieves higher success rates in circumventing adversarial defense mechanisms.

Paper proposes a method to detect adversarial examples that can resist norm-constrained attacks.

problem Vulnerabilities of deep neural networks to adversarial examples in sensitive domains.
method Train K binary classifiers to distinguish between clean data and adversarially perturbed samples, use at test time to classify inputs.
result Proposed method can resist norm-constrained white-box attacks.

Detects adversarial examples using SHAP values from neural networks.

problem Vulnerability of deep neural networks to adversarial attacks.
method Uses SHAP values from internal layers to distinguish normal from adversarial inputs.
result Demonstrates high detection accuracy and strong generalization to various attack methods.

CCAT improves model robustness to various adversarial attacks.

problem Robustness to adversarial attacks does not generalize to unseen threat models.
method CCAT biases models towards low confidence predictions on adversarial examples.
result CCAT increases robustness against multiple adversarial attack norms and types.

A two-step defense method generates strong adversarial examples at low cost.

problem Vulnerability of deep neural networks to adversarial attacks.
method Develops a two-step defense approach that generates strong adversarial examples using FGSM at a lower computational cost compared to traditional multi-step adversarial training.
result Demonstrates effectiveness of the two-step defense approach against various attack methods with comparable robustness to traditional multi-step adversarial training.

This paper proposes SPT to generate diverse and transferable adversarial examples.

problem Limitations of recent adversarial examples in diversity and transferability.
method Structure-preserving transformation (SPT) to generate natural and diverse adversarial examples.
result Adversarial examples generated by SPT transfer well to other models with high success rate.

SPAT improves adversarial robustness by preserving semantics in adversarial training.

problem Adversarial examples often have different semantics than original data, introducing unintended biases.
method Semantics-preserving adversarial training (SPAT) that encourages pixel perturbation shared among all classes.
result SPAT improves adversarial robustness and achieves state-of-the-art results in CIFAR-10 and CIFAR-100.

Enhances adversarial examples for better transferability across models.

problem Adversarial examples often have limited black-box transferability.
method Fine-tunes existing adversarial examples by increasing perturbation on a pre-specified layer of the source model.
result Our method achieves greater black-box transferability of adversarial examples.

Study on adversarial examples and defenses for malware classification.

problem Vulnerability of neural networks to adversarial examples in malware classification.
method Analysis of different approaches for crafting adversarial examples and defense techniques in malware domain.
result Comparison of effectiveness of different approaches on multiple datasets.

This paper shows excessive invariance in adversarial robust models can make them more vulnerable to certain types of attacks.

problem Excessive invariance in adversarial robust models can make them more vulnerable to certain types of attacks.
method Analytical constructions and empirical studies of vision classifiers with state-of-the-art robustness to perturbation-based adversaries constrained by an p\ell_p norm.
result Robustness to perturbation-based adversarial examples does not guarantee general robustness and can increase vulnerability to invariance-based adversarial examples.

This paper explores how the generalization of substitute classifiers affects the success of black-box adversarial attacks.

problem Understanding the factors driving the transferability of black-box adversarial examples.
method Max-min adversarial example game framework and theoretical generalization bounds.
result Substitute NN with better generalization behavior results in more transferable adversarial examples.

The paper connects higher order risk measures and stochastic dominance, showing their equivalence and integrating them with optimization.

problem Comparing and characterizing random outcomes in risk assessment.
method Exploring the equivalence between higher order risk measures and stochastic dominance, using stochastic optimization and expectiles as examples.
result Higher order risk measures and stochastic dominance are equivalent and can be used to characterize random outcomes.

Transform images with adversarial examples for robust classification.

problem Adversarial examples mislead deep neural networks in image classification.
method Transform input images with adversarial examples from a pre-trained model.
result Significantly more robust against a wide range of attacks compared to state-of-the-art methods.

A novel method to train networks from each other's adversarial examples to resist black-box attacks.

problem Machine learning models can be fooled by adversarial examples, especially in black-box attacks.
method Simultaneous adversarial training combining two networks to learn from each other's adversarial examples.
result The method improves the networks' resilience to black-box attacks.