Related papers: Mitigating the Backdoor Effect for Multi-Task Mode…

With the rapid growth of deep learning, there is an increasing availability of open-source models for various tasks. However, single fine-tuned models often fall short of meeting the diverse needs of users. Model merging has thus emerged as…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

For millimeter wave (mmWave) or Terahertz (THz) communications, by leveraging the high spatial resolution offered by large antenna arrays and the multi-path sparsity of mmWave/THz channels, a novel inter-symbol interference (ISI) mitigation…

Machine learning (ML) has made tremendous progress during the past decade and is being adopted in various critical real-world applications. However, recent research has shown that ML models are vulnerable to multiple security and privacy…

As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm. In this paper, we investigate the interplay between vulnerabilities of the image scaling…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct models with different initializations, each solving a…

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Model merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the specialized capabilities of these LLMs. Most task-specific…

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…

Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing…

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification…

In driving scenarios, automobile active safety systems are increasingly incorporating deep learning technology. These systems typically need to handle multiple tasks simultaneously, such as detecting fatigue driving and recognizing the…

This paper introduces delay-alignment modulation (DAM) for secure integrated sensing and communication (ISAC). Due to the broadcast nature of multi-user downlinks, communications are vulnerable to eavesdropping. DAM applies controlled…

Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model…

Model merging enables the combination of multiple specialized expert models into a single model capable of performing multiple tasks. However, the benefits of merging an increasing amount of specialized experts generally lead to diminishing…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Recent multi-modal face anti-spoofing (FAS) methods have investigated the potential of leveraging multiple modalities to distinguish live and spoof faces. However, pre-adapted multi-modal FAS models often fail to detect unseen attacks from…