相关论文: Single-Class Target-Specific Attack against Interp…

In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained…

Machine learning models are susceptible to adversarial perturbations: small changes to input that can cause large changes in output. It is also demonstrated that there exist input-agnostic perturbations, called universal adversarial…

The adversarial attack can force a CNN-based model to produce an incorrect output by craftily manipulating human-imperceptible input. Exploring such perturbations can help us gain a deeper understanding of the vulnerability of neural…

Deep Learning models, such as those used in an autonomous vehicle are vulnerable to adversarial attacks where an attacker could place an adversarial object in the environment, leading to mis-classification. Generating these adversarial…

Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models. To improve the transferability of adversarial…

Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existing methods for semantic classification typically employ…

Adversarial perturbations have drawn great attentions in various deep neural networks. Most of them are computed by iterations and cannot be interpreted very well. In contrast, little attentions are paid to basic machine learning models…

This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. We propose a novel…

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of…

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

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…

Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…

Unified vision-language models(VLMs) have recently shown remarkable progress, enabling a single model to flexibly address diverse tasks through different instructions within a shared computational architecture. This instruction-based…

Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

The dangers of adversarial attacks on Uncrewed Aerial Vehicle (UAV) agents operating in public are increasing. Adopting AI-based techniques and, more specifically, Deep Learning (DL) approaches to control and guide these UAVs can be…

Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel concepts. As these models gain traction in high-stakes…

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against…