Latest Articles for Adversarial Attacks

Introducing adversarial hypervolume to better assess deep learning model performance.

This paper discusses adversarial training for robust quantum machine learning classifiers.

A new approach improves model performance against distribution shifts and adversarial attacks.

Improving robustness against adversarial attacks in vision-language models.

This article reviews the robustness of CLIP in various challenges.

A proposed framework enhances security for federated learning against adversarial attacks.

This article reviews the strengths and weaknesses of the VMamba model.

A look at threats posed by LLMs and strategies for defense.

Examining the role of deep learning in medical image analysis and adversarial threats.

Tropical neural networks enhance resilience against adversarial attacks in machine learning.

This article examines how adversarial attacks alter the learned concepts of CNNs.

Examining how adversarial attacks affect AI predictions and explanations.

A novel approach enhances language model reliability through self-healing mechanisms.

Understanding the impact of adversarial attacks on machine learning models.

This article examines how adversarial attacks compromise text classification models.

Enhancing tools to detect harmful language in online spaces is crucial for safety.

A new method enhances visual object tracking resilience against subtle attacks.

Learn about adversarial attacks and their impact on machine learning models.

Exploring key factors affecting robustness against adversarial attacks in machine learning.

New method reveals vulnerabilities in no-reference image and video quality assessments.

Examining PDMs' security against adversarial attacks in image creation.

A method to increase classifier reliability against data manipulation.

A look at the security threats posed by instruction-tuned Code LLMs.

This article discusses enhancing CNNs by leveraging low-frequency information for better resilience against adversarial attacks.

This study examines the weaknesses of SER models against adversarial attacks across languages.

Box-NN enhances model performance against adversarial challenges with simplicity and efficiency.

A universal audio clip can mute advanced ASR models like Whisper.

New layer pruning technique enhances model efficiency and accuracy.

This study improves the security of quantum machine learning against adversarial attacks through noise channels and privacy methods.

This article investigates vulnerabilities in speech models and ways to enhance their security.

A new defense mechanism improves object detection in drones under adversarial threats.

This study evaluates transformer trackers against adversarial attacks in object tracking.

SCRN offers a reliable way to identify AI-generated content effectively.

Exploring the challenges of GNN explainers under adversarial attacks in critical applications.

New method enhances uncertainty quantification in adversarially trained models.

New method reveals vulnerabilities in Vision-Language Pre-training models through universal adversarial perturbations.

RC-NAS framework enhances deep learning models against adversarial attacks effectively.

New method reveals vulnerabilities in GNN explanation methods.

Study examines the robustness of segmentation models against adversarial attacks in healthcare.

A new approach enhances the robustness of Vision Transformers against adversarial attacks.