相关论文: BESA: Boosting Encoder Stealing Attack with Pertur…

We consider a communication scenario, in which an intruder tries to determine the modulation scheme of the intercepted signal. Our aim is to minimize the accuracy of the intruder, while guaranteeing that the intended receiver can still…

This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptimal performances attributed to biased optimization objectives,…

Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to downstream tasks. Behind their revolutionary representation…

Defense strategies have been well studied to combat Byzantine attacks that aim to disrupt cooperative spectrum sensing by sending falsified versions of spectrum sensing data to a fusion center. However, existing studies usually assume…

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms…

Deep learning technologies are pivotal in enhancing the performance of WiFi-based wireless sensing systems. However, they are inherently vulnerable to adversarial perturbation attacks, and regrettably, there is lacking serious attention to…

Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations. However, the…

Deep machine learning models are increasingly deployedin the wild for providing services to users. Adversaries maysteal the knowledge of these valuable models by trainingsubstitute models according to the inference results of thetargeted…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the…

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker…

According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns to perform tasks…

In challenging environments with significant noise and reverberation, traditional speech enhancement (SE) methods often lead to over-suppressed speech, creating artifacts during listening and harming downstream tasks performance. To…

Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…

This paper presents a novel yet efficient defense framework for segmentation models against adversarial attacks in medical imaging. In contrary to the defense methods against adversarial attacks for classification models which widely are…

Traditional security detection methods face three key challenges: inadequate data collection that misses critical security events, resource-intensive monitoring systems, and poor detection algorithms with high false positive rates. We…

Binary code similarity analysis (BCSA) serves as a foundational technique for binary analysis tasks such as vulnerability detection and malware identification. Existing graph based BCSA approaches capture more binary code semantics and…

Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costly to train, they become lucrative targets for model stealing…

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…