Related papers: BeDKD: Backdoor Defense Based on Directional Mappi…

Neural networks (NNs) are already deployed in hardware today, becoming valuable intellectual property (IP) as many hours are invested in their training and optimization. Therefore, attackers may be interested in copying, reverse…

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…

Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model. Existing defenses for backdoor…

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

Regarding intelligent transportation systems, low-bitrate transmission via lossy point cloud compression is vital for facilitating real-time collaborative perception among connected agents, such as vehicles and infrastructures, under…

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…

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…

Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, despite the presence of both benign and trigger information.…

Multimodal learning that integrates genomics and histopathology has shown strong potential in cancer diagnosis, yet its clinical translation is hindered by the limited availability of paired histology-genomics data. Knowledge distillation…

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Research has proven that end-to-end malware detectors are vulnerable to adversarial attacks. In response, the research community has proposed defenses based on randomized and (de)randomized smoothing. However, these techniques remain…

Large language models for code have achieved strong performance across diverse software analytics tasks, yet their real-world adoption remains limited by high computational demands, slow inference speeds, significant energy consumption, and…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning.…

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that…

Dataset distillation (DD) allows datasets to be distilled to fractions of their original size while preserving the rich distributional information, so that models trained on the distilled datasets can achieve a comparable accuracy while…