arXiv:2608. 10237v1 Announce Type: new Abstract: Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification boundaries, but by relational geometry in embedding space.
arXiv:2605. 31219v2 Announce Type: replace-cross Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations.
arXiv:2607. 07089v1 Announce Type: new Abstract: Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction.
Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction. We study the adversarial robustness of this pipeline.
arXiv:2607. 14737v1 Announce Type: cross Abstract: Vision-language pre-trained models (VLPs) are widely used in real-world applications.
arXiv:2412. 08394v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions.
The paper introduces Manifold Anchored Bilevel Transfer (MABT), a framework that aligns adversarial attack trajectories with the intrinsic data manifold to reduce surrogate-specific overfitting. MABT employs a relaxed manifold-anchoring operator as a semantic rectifier and formulates transfer attack generation as a distributional bilevel optimization problem, learning geometry-aligned initializations that minimize expected transfer risk. A Hessian-free solver with linear-time complexity is developed to efficiently solve the resulting hierarchy, and experiments show improved transferability across 10 attackers, 28 configurations, various victim models, and defense mechanisms.
FSPGD introduces a feature-space black-box attack for semantic segmentation that targets intermediate representations rather than just output logits. The method uses a dual loss: an external loss to disrupt cross-model feature alignment and an internal loss to reduce consistency among same-class instances. Experiments on Pascal VOC 2012 and Cityscapes show that FSPGD outperforms existing logit-level and segmentation-specific attacks across CNN and Transformer backbones, and its adversarial examples improve robustness when used for training.
arXiv:2608.29510v1 Announce Type: cross Abstract: Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches...
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector...
arXiv:2406. 09250v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses.
arXiv:2608.29054v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly i...
arXiv:2509. 01235v2 Announce Type: replace Abstract: Balancing training accuracy and adversarial robustness has beeen a challenge since the birth of deep learning.