Related papers: Adversarial CAPTCHAs
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…
Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show that unrolling this gradient-based optimization…
Defending against physical adversarial attacks is a rapidly growing topic in deep learning and computer vision. Prominent forms of physical adversarial attacks, such as overlaid adversarial patches and objects, share similarities with…
Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…
Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers. Building a robust, frequently asked questions (FAQ) chatbot needs a large amount of diverse adversarial examples. Recent question…
The design of the defenses Internet systems can deploy against attack, especially adaptive and resilient defenses, must start from a realistic model of the threat. This requires an assessment of the capabilities of the adversary. The design…
With the advent of generative adversarial networks, synthesizing images from textual descriptions has recently become an active research area. It is a flexible and intuitive way for conditional image generation with significant progress in…
Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…
Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…
As a result of continuing advances in computer capabilities, it is becoming increasingly difficult to distinguish between humans and computers in the digital world. We propose using the fundamental human ability to distinguish between…
This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It involves applying gradient-based perturbation on the sentence…
Malicious intelligent algorithms greatly threaten the security of social users' privacy by detecting and analyzing the uploaded photos to social network platforms. The destruction to DNNs brought by the adversarial attack sparks the…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…
Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of…
The rise of text-to-image (T2I) models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial…
We provide a complete characterisation of the phenomenon of adversarial examples - inputs intentionally crafted to fool machine learning models. We aim to cover all the important concerns in this field of study: (1) the conjectures on the…
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…
Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…
Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a cross-border language, is gradually being studied due to its…