Related papers: Adversarial Detection Avoidance Attacks: Evaluatin…

Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to adversarial examples, which can cause fateful consequences in…

We consider an echo-assisted communication model wherein block-coded messages, when transmitted across several frames, reach the destination as multiple noisy copies. We address adversarial attacks on such models wherein a subset of the…

In this paper, we assess existing technical proposals for content moderation in End-to-End Encryption (E2EE) services. First, we explain the various tools in the content moderation toolbox, how they are used, and the different phases of the…

Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions.…

Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…

End-to-End Encryption (E2EE) ensures that only the intended recipient(s) can read messages. Popular instant messaging (IM) applications such as Signal, WhatsApp, Apple's iMessage, and Telegram claim to offer E2EE. However, client-side…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

We explore an emerging threat model for end-to-end (E2E) encrypted applications: an adversary sends chosen messages to a target client, thereby "injecting" adversarial content into the application state. Such state is subsequently encrypted…

Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important,…

Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition…

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

We propose adversarial embedding, a new steganography and watermarking technique that embeds secret information within images. The key idea of our method is to use deep neural networks for image classification and adversarial attacks to…

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…

Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society. Many methods have been proposed to detect fake images, but they are vulnerable to adversarial perturbations…

Deep neural networks have empowered accurate device-free human activity recognition, which has wide applications. Deep models can extract robust features from various sensors and generalize well even in challenging situations such as…

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape…

Deep Neural Networks have been shown to be vulnerable to adversarial images. Conventional attacks strive for indistinguishable adversarial images with strictly restricted perturbations. Recently, researchers have moved to explore…

Transferable adversarial images raise critical security concerns for computer vision systems in real-world, black-box attack scenarios. Although many transfer attacks have been proposed, existing research lacks a systematic and…

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks…