Related papers: Universal Adversarial Attacks with Natural Trigger…
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…
Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…
This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP models. Our poisoning attack utilizes conditional…
Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…
This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…
Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generating natural language…
An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…
Adversarial input image perturbation attacks have emerged as a significant threat to machine learning algorithms, particularly in image classification setting. These attacks involve subtle perturbations to input images that cause neural…
Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…
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…
The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to efficiently generate adversarial attacks, some of them relying on…
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant…
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…
In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…
Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…
Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…
Recently, with the advancement of deep learning, several applications in text classification have advanced significantly. However, this improvement comes with a cost because deep learning is vulnerable to adversarial examples. This weakness…
Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…