Related papers: Distillation-Enhanced Physical Adversarial Attacks
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object.…
Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…
We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing…
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…
Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks. The typical way of conducting knowledge distillation is to train the student network under the supervision of the teacher network to…
Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…
Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…
Physical adversarial patch (PAP) attacks attach carefully crafted patches to physical objects to manipulate a deployed model. However, existing PAP attacks suffer from several limitations. First, existing patches remain continuously active,…
Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into consideration, like glasses,…
Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…
Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for…
Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…
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…
Adversarial attacks on deep learning models have received increased attention in recent years. Work in this area has mostly focused on gradient-based techniques, so-called 'white-box' attacks, where the attacker has access to the targeted…
The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against…
Adversarial Robustness Distillation (ARD) has emerged as an effective method to enhance the robustness of lightweight deep neural networks against adversarial attacks. Current ARD approaches have leveraged a large robust teacher network to…
Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Although many face anti-spoofing (FAS) methods perform well in…
Significant memory and computational requirements of large deep neural networks restrict their application on edge devices. Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the…