相关论文: Fine-mixing: Mitigating Backdoors in Fine-tuned La…

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high computational resources…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.…

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Human language encompasses a wide range of intricate and diverse implicit features, which attackers can exploit to launch adversarial or backdoor attacks, compromising DNN models for NLP tasks. Existing model-oriented defenses often require…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Recently, deep neural networks (DNNs) have been deployed in safety-critical systems such as autonomous vehicles and medical devices. Shortly after that, the vulnerability of DNNs were revealed by stealthy adversarial examples where crafted…

When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs. Currently, a large number of researches on defending adversarial…

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…

One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backdoor attacks on deep neural networks (DNNs) in the production…

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed…

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…

Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger reverse engineering and often require clean samples or…