arXiv AI
Jun 17
Adversarial Attacks Leverage Interference Between Features in Superposition
arXiv:2510. 11709v2 Announce Type: replace-cross Abstract: Why do adversarial examples exist, and why do they transfer between models?
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
arXiv:2606. 26207v1 Announce Type: cross Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry.
Related stories
arXiv AI
Aug 12
Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry
arXiv:2505. 22839v2 Announce Type: replace-cross Abstract: Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models.
arXiv Machine Learning
Jun 26
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
arXiv Machine Learning
Aug 6
One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
arXiv Machine Learning
Jul 21
Geometric origin of adversarial vulnerability in deep learning
arXiv:2509. 01235v2 Announce Type: replace Abstract: Balancing training accuracy and adversarial robustness has beeen a challenge since the birth of deep learning.
arXiv AI
Jul 14
Enhancing Adversarial Transferability through Block Stretch and Shrink
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
arXiv AI
Jun 10
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
arXiv Machine Learning
Jul 17
GeoDetect: Geometric Adversarial Detection for VLPs
arXiv:2607. 14737v1 Announce Type: cross Abstract: Vision-language pre-trained models (VLPs) are widely used in real-world applications.
arXiv Machine Learning
Jul 15
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.
Hugging Face Trending Papers
Jun 2
Investigating Adversarial Robustness of Multi-modal Large Language Models
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
arXiv Machine Learning
Jul 7
Binary Iterative Method for Non-targeted Adversarial Attack
arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.
arXiv Machine Learning
1d ago
Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation
arXiv:2608. 14594v1 Announce Type: new Abstract: Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack.