相关论文: Boosting Adversarial Transferability via Ensemble …

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…

Deep learning surrogate models are being increasingly used in accelerating scientific simulations as a replacement for costly conventional numerical techniques. However, their use remains a significant challenge when dealing with real-world…

Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing adoption raises serious security concerns,…

Recent medical image segmentation models are mostly hybrid, which integrate self-attention and convolution layers into the non-isomorphic architecture. However, one potential drawback of these approaches is that they failed to provide an…

Attention mechanisms have raised significant interest in the research community, since they promise significant improvements in the performance of neural network architectures. However, in any specific problem, we still lack a principled…

Recent architectural developments have enabled recurrent neural networks (RNNs) to reach and even surpass the performance of Transformers on certain sequence modeling tasks. These modern RNNs feature a prominent design pattern: linear…

Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…

With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in…

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…

Attention mechanisms have become a cornerstone in modern neural networks, driving breakthroughs across diverse domains. However, their application to graph structured data, where capturing topological connections is essential, remains…

Introduction. We investigate the generalization ability of models built on datasets containing a small number of subjects, recorded in single study protocols. Next, we propose and evaluate methods combining these datasets into a single,…

Transfer-based attacks craft adversarial examples on white-box surrogate models and directly deploy them against black-box target models, offering model-agnostic and query-free threat scenarios. While flatness-enhanced methods have recently…

Adversarial transferability remains a critical challenge in evaluating the robustness of deep neural networks. In security-critical applications, transferability enables black-box attacks without access to model internals, making it a key…

While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored. We identify that the domain gap can cause discrepancies in self-attention. Due to this gap, the…

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of…

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent…

In recent years, the convolutional neural networks (CNNs) have received a lot of interest in the side-channel community. The previous work has shown that CNNs have the potential of breaking the cryptographic algorithm protected with masking…

Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this…

Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model…

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to…