Related papers: Towards Crafting Text Adversarial Samples
Neural text detectors aim to decide the characteristics that distinguish neural (machine-generated) from human texts. To challenge such detectors, adversarial attacks can alter the statistical characteristics of the generated text, making…
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…
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…
Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…
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 artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classification, especially…
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution…
Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…
Wake-up word detection models are widely used in real life, but suffer from severe performance degradation when encountering adversarial samples. In this paper we discuss the concept of confusing words in adversarial samples. Confusing…
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…
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…
Most current methods generate adversarial examples with the $L_p$ norm specification. As a result, many defense methods utilize this property to eliminate the impact of such attacking algorithms. In this paper,we instead introduce…
We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging…
Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…
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…
Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…
Adversarial classification is the task of performing robust classification in the presence of a strategic attacker. Originating from information hiding and multimedia forensics, adversarial classification recently received a lot of…
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…
The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues. For many safety-critical ML tasks, such as financial forecasting, fraudulent detection, and anomaly…
Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples…