To address this problem, we are the first to investigate defense strategies against adversarial patch attacks on infrared detection, especially human detection.
Specifically, VoteTRANS detects adversarial text by comparing the hard labels of input text and its transformation.
We introduce a method for detecting manipulated videos that is based on the trajectory of the facial region displacement.
The results raise the alarm about the robustness of such systems and suggest that master vein attacks should be considered an important security measure.
We have investigated a new application of adversarial examples, namely location privacy protection against landmark recognition systems.
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.
Recent advances in deep learning have led to substantial improvements in deepfake generation, resulting in fake media with a more realistic appearance.
Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model's predictions.
The dataset is available at https://doi. org/10. 5281/zenodo. 8208877 .
However, there is still a lack of comprehensive research on both methodologies and datasets.
We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e. g., M-BERT).
Previous work has proven the existence of master faces, i. e., faces that match multiple enrolled templates in face recognition systems, and their existence extends the ability of presentation attacks.
To promote these new tasks, we have created the first large-scale dataset posing a high level of challenges that is designed with face-wise rich annotations explicitly for face forgery detection and segmentation, namely OpenForensics.
Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility.
It generates adversarial textures learned from fashion style images and then overlays them on the clothing regions in the original image to make all persons in the image invisible to person segmentation networks.
In this work, we demonstrated that wolf (generic) faces, which we call "master faces," can also compromise face recognition systems and that the master face concept can be generalized in some cases.
Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry.
We experimentally demonstrated the existence of individual adversarial perturbations (IAPs) and universal adversarial perturbations (UAPs) that can lead a well-performed FFM to misbehave.
The rapid development of deep learning techniques has created new challenges in identifying the origin of digital images because generative adversarial networks and variational autoencoders can create plausible digital images whose contents are not present in natural scenes.
In this paper, we introduce a capsule network that can detect various kinds of attacks, from presentation attacks using printed images and replayed videos to attacks using fake videos created using deep learning.
Advanced neural language models (NLMs) are widely used in sequence generation tasks because they are able to produce fluent and meaningful sentences.
The output of one branch of the decoder is used for segmenting the manipulated regions while that of the other branch is used for reconstructing the input, which helps improve overall performance.
One solution to mitigate these concerns involves the concealing of speaker identities before the sharing of speech data.
We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences.
Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and for the generated target speaker to appear and sound natural.
Recent advances in media generation techniques have made it easier for attackers to create forged images and videos.
This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face.
Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security.
Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data.
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database.