Related papers: Leveraging Extracted Model Adversaries for Improve…
Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…
While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on image-to-text models require access to the architecture,…
Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…
Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks, it might not be computationally or informationally feasible…
Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…
Machine learning has achieved great success in many applications, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). Unfortunately, many machine learning models are vulnerable to adversarial examples, which are…
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) to specifically…
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…
With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…
The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…
Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…
Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is still challenging to efficiently produce targeted…
Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attention to adversarial examples, there has been a flood of research into defending and attacking machine learning models. However, almost all proposed attacks assume…
With further development in the fields of computer vision, network security, natural language processing and so on so forth, deep learning technology gradually exposed certain security risks. The existing deep learning algorithms cannot…
Understanding adversarial examples is crucial for improving model robustness, as they introduce imperceptible perturbations to deceive models. Effective adversarial examples, therefore, offer the potential to train more robust models by…
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…
Adversarial attacks remain a significant threat that can jeopardize the integrity of Machine Learning (ML) models. In particular, query-based black-box attacks can generate malicious noise without having access to the victim model's…
Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…
We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context,…
Traffic state prediction is necessary for many Intelligent Transportation Systems applications. Recent developments of the topic have focused on network-wide, multi-step prediction, where state of the art performance is achieved via deep…