相关论文: Injecting Undetectable Backdoors in Obfuscated Neu…

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via progressive noise-addition and denoising. To gain a better…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We challenge this assumption by introducing implicit memory-the…

Federated learning has seen increased adoption in recent years in response to the growing regulatory demand for data privacy. However, the opaque local training process of federated learning also sparks rising concerns about model…

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on…

Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden…

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary…

Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for…

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned…

With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt…

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Mixture-of-Experts (MoE) have emerged as a powerful architecture for large language models (LLMs), enabling efficient scaling of model capacity while maintaining manageable computational costs. The key advantage lies in their ability to…

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial…