Image forensic plays a crucial role in both criminal investigations (eg, dissemination of fake
images to spread racial hate or false narratives about specific ethnicity groups or political …

As the field of deep learning experiences a meteoric rise, the urgency to decipher the
complex geometric properties of feature spaces, which underlie the effectiveness of diverse …

Deep learning algorithms provide state-of-the-art results on a multitude of applications.
However, it is also well established that they are highly vulnerable to adversarial …

In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed,
pre-trained model at test time. Compared to conventional adversarial defenses, VP allows …

Meta learning is a promising paradigm to enable skill transfer across tasks. Most previous
methods employ the empirical risk minimization principle in optimization. However, the …

自动目标识别(ATR) 是一个和信号与信息处理, 模式识别, 人工智能等学科密切相关的特殊工程
技术应用领域. 由于ATR 系统识别对象固有的不确定性, 识别环境的复杂性 …

Adversarial perturbations aim to modify the image pixels in an imperceptible manner such
that the CNN classifier misclassifies an image, whereas humans can predict the original …

The use of medical images for colon cancer detection is considered an important problem.
As the performance of data-driven methods relies heavily on the images generated by a …

Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms
to adversarial attacks. Existing adversary detection algorithms attempt to detect the …

Although recent deep neural network algorithm has shown tremendous success in several
computer vision tasks, their vulnerability against minute adversarial perturbations has raised …