Related papers: PuriDefense: Randomized Local Implicit Adversarial…

Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient,…

Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this…

While deep neural networks show unprecedented performance in various tasks, the vulnerability to adversarial examples hinders their deployment in safety-critical systems. Many studies have shown that attacks are also possible even in a…

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of…

Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security risks, including deepfakes and copyright infringement. In…

Backdoor attacks pose a significant threat to deep neural networks, particularly as recent advancements have led to increasingly subtle implantation, making the defense more challenging. Existing defense mechanisms typically rely on an…

Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful information such as the…

Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic…

In recent years, Deep Neural Networks (DNNs) have had a dramatic impact on a variety of problems that were long considered very difficult, e. g., image classification and automatic language translation to name just a few. The accuracy of…

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images. To defend against adversarial attacks in a training-free and attack-agnostic manner, this…

The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even when, as is the case in many practical settings, the classifier is hosted as a remote service…

The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of the model itself…

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications. However, recent studies observe gradient-masking defenses are self-deceiving methods if an attacker can realize this…

Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to recognize images of animals can be reprogrammed to…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious threat to deep learning-based systems compromising their…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…