相关论文: Mind the box: $l_1$-APGD for sparse adversarial at…

In this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a synergistic robustness-enhancing way. The method builds upon…

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on…

Adversarial examples contain small perturbations that can remain imperceptible to human observers but alter the behavior of even the best performing deep learning models and yield incorrect outputs. Since their discovery, adversarial…

Deep neural networks are found to be prone to adversarial examples which could deliberately fool the model to make mistakes. Recently, a few of works expand this task from 2D image to 3D point cloud by using global point cloud optimization.…

Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.…

3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction. However, its per-scene optimization pipeline limits scalability and generalization, and prevents efficient…

In the past few years, Generative Adversarial Networks (GANs) have dramatically advanced our ability to represent and parameterize high-dimensional, non-linear image manifolds. As a result, they have been widely adopted across a variety of…

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…

In this work we explore the fundamental structure-adaptiveness of state of the art randomized first order algorithms on regularized empirical risk minimization tasks, where the solution has intrinsic low-dimensional structure (such as…

We present preconditioned stochastic gradient descent (SGD) algorithms for the $\ell_1$ minimization problem $\min_{x}\|A x - b\|_1$ in the overdetermined case, where there are far more constraints than variables. Specifically, we have $A…

Adversarial attack has recently become a tremendous threat to deep learning models. To improve the robustness of machine learning models, adversarial training, formulated as a minimax optimization problem, has been recognized as one of the…

Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a lot of defense methods were proposed, which however, have been circumvented by newer attacking strategies. In the midst of this…

CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…

Gradient inversion attacks are often presented as a serious privacy threat in federated learning, with recent work reporting increasingly strong reconstructions under favorable experimental settings. However, it remains unclear whether such…

This paper considers the decision-dependent optimization problem, where the data distributions react in response to decisions affecting both the objective function and linear constraints. We propose a new method termed repeated projected…

In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…

Deep learning models have shown incredible performance on numerous image recognition, classification, and reconstruction tasks. Although very appealing and valuable due to their predictive capabilities, one common threat remains challenging…