Related papers: Dithering Defense: Adversarial Robustness of Visio…

Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to…

We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the…

Deep hashing models have been widely adopted to tackle the challenges of large-scale image retrieval. However, these approaches face serious security risks due to their vulnerability to adversarial examples. Despite the increasing…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work,…

Recent developments in adversarial machine learning have highlighted the importance of building robust AI systems to protect against increasingly sophisticated attacks. While frameworks like AI Guardian are designed to defend against these…

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image…

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional…

Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic…

Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning…

Advancing face morphing attack techniques is crucial to anticipate evolving threats and develop robust defensive mechanisms for identity verification systems. This work introduces DCMorph, a dual-stream diffusion-based morphing framework…

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the…

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc…

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have…

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…

The design of a security scheme for beamforming prediction is critical for next-generation wireless networks (5G, 6G, and beyond). However, there is no consensus about protecting the beamforming prediction using deep learning algorithms in…

The rapid evolution of generative adversarial networks (GANs) and diffusion models has made synthetic media increasingly realistic, raising societal concerns around misinformation, identity fraud, and digital trust. Existing deepfake…

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…