Related papers: Efficiently Attacking Memorization Scores
Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…
Adversarial ranking attacks have gained increasing attention due to their success in probing vulnerabilities, and, hence, enhancing the robustness, of neural ranking models. Conventional attack methods employ perturbations at a single…
Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…
While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable…
Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…
Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…
Deep learning models for time series imputation are now essential in fields such as healthcare, the Internet of Things (IoT), and finance. However, their deployment raises critical privacy concerns. Beyond the well-known issue of unintended…
Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data…
Transferability of adversarial samples became a serious concern due to their impact on the reliability of machine learning system deployments, as they find their way into many critical applications. Knowing factors that influence…
Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…
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 attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…
Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…
Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their…
Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions. Inspired by this phenomenon, we explore the feasibility of manipulating EEG-based Motor Imagery (MI) Brain…
With the advent of deep learning methods, Neural Machine Translation (NMT) systems have become increasingly powerful. However, deep learning based systems are susceptible to adversarial attacks, where imperceptible changes to the input can…
Machine unlearning (MUL) focuses on removing the influence of specific subsets of data (such as noisy, poisoned, or privacy-sensitive data) from pretrained models. MUL methods typically rely on specialized forms of fine-tuning. Recent…
Deep learning models suffer from a phenomenon called adversarial attacks: we can apply minor changes to the model input to fool a classifier for a particular example. The literature mostly considers adversarial attacks on models with images…
There has long been debates on how we could interpret neural networks and understand the decisions our models make. Specifically, why deep neural networks tend to be error-prone when dealing with samples that output low softmax scores. We…