Related papers: Zero-Query Transfer Attacks on Context-Aware Objec…
Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…
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,…
Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models.…
Event cameras, known for their low latency and high dynamic range, show great potential in pedestrian detection applications. However, while recent research has primarily focused on improving detection accuracy, the robustness of…
Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by…
Anomaly detection is a method for discovering unusual and suspicious behavior. In many real-world scenarios, the examined events can be directly linked to the actions of an adversary, such as attacks on computer networks or frauds in…
Recent advances of deep learning have brought exceptional performance on many computer vision tasks such as semantic segmentation and depth estimation. However, the vulnerability of deep neural networks towards adversarial examples have…
Deep neural networks have demonstrated remarkable effectiveness across a wide range of tasks such as semantic segmentation. Nevertheless, these networks are vulnerable to adversarial attacks that add imperceptible perturbations to the input…
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences…
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the…
Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…
We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image, our method operates on an entire concept - represented by…
This paper explores a scenario in which a malicious actor employs a multi-armed attack strategy to manipulate data samples, offering them various avenues to introduce noise into the dataset. Our central objective is to protect the data by…
Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…
There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversarial samples within a given perturbation level. The second…
Prompt injection remains a major security risk for large language models. However, the efficacy of existing guardrail models in context-aware settings remains underexplored, as they often rely on static attack benchmarks. Additionally, they…
Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks…
Studying adversarial attacks on artificial intelligence (AI) systems helps discover model shortcomings, enabling the construction of a more robust system. Most existing adversarial attack methods only concentrate on single-task single-model…
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…