Related papers: Preventing Distillation-based Attacks on Neural Ne…
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning…
The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software platforms. They also allow for more open…
This technical report delves into an in-depth exploration of adversarial attacks specifically targeted at Deep Neural Networks (DNNs) utilized for image classification. The study also investigates defense mechanisms aimed at bolstering the…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Due to significant improvements in performance in recent years, neural networks are currently used for an ever-increasing number of applications. However, neural networks have the drawback that their decisions are not readily interpretable…
Thermally coupled distillation is a new energy-saving method, but the traditional thermally coupled distillation simulation calculation process is complicated, and the optimization method based on the traditional simulation process is…
Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. However, there…
Knowledge distillation can lead to deploy-friendly networks against the plagued computational complexity problem, but previous methods neglect the feature hierarchy in detectors. Motivated by this, we propose a general framework for…
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning…
The carbon footprint of natural language processing research has been increasing in recent years due to its reliance on large and inefficient neural network implementations. Distillation is a network compression technique which attempts to…
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from…
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…
Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The main risk is not merely copying, but the possibility that useful capability can be transferred more cheaply than the governance…
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the…
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…
Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…
Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and…
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…
Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…