Related papers: Generating Watermarked Adversarial Texts
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…
With the recent developments in artificial intelligence and machine learning, anomalies in network traffic can be detected using machine learning approaches. Before the rise of machine learning, network anomalies which could imply an…
Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…
Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…
Most machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset,…
Sequence-based deep learning models (e.g., RNNs), can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence…
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial…
Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification becomes popular…
Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…
Technologies of the Internet of Things (IoT) facilitate digital contents such as images being acquired in a massive way. However, consideration from the privacy or legislation perspective still demands the need for intellectual content…
As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversarial examples are…
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…
Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…
Deep generative models are rapidly becoming a common tool for researchers and developers. However, as exhaustively shown for the family of discriminative models, the test-time inference of deep neural networks cannot be fully controlled and…
We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives. Prior methods either produce easily detectable gibberish, or cannot…
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted…
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a…
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the…
Deep Neural Networks (DNNs) are everywhere, frequently performing a fairly complex task that used to be unimaginable for machines to carry out. In doing so, they do a lot of decision making which, depending on the application, may be…