相关论文: BLAST: A Stealthy Backdoor Leverage Attack against…

Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $\pi_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation…

Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside…

As artificial intelligence becomes more prevalent in our lives, people are enjoying the convenience it brings, but they are also facing hidden threats, such as data poisoning and adversarial attacks. These threats can have disastrous…

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…

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple tasks. However, existing model merging techniques primarily…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the inputs containing triggers. Most previous backdoor attacks mainly…

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Federated learning (FL) has been widely adopted as a decentralized training paradigm that enables multiple clients to collaboratively learn a shared model without exposing their local data. As concerns over data privacy and regulatory…

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Prototype-based federated learning (PFL) has emerged as a promising paradigm to address data heterogeneity problems in federated learning, as it leverages mean feature vectors as prototypes to enhance model generalization. However, its…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Federated Contrastive Learning (FCL) is an emerging privacy-preserving paradigm in distributed learning for unlabeled data. In FCL, distributed parties collaboratively learn a global encoder with unlabeled data, and the global encoder could…

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…

Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's…