Related papers: Frequency-Domain Regularized Adversarial Alignment…

Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discriminator overfitting. To tackle this issue, we investigate the…

In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial false-positive rates under realistic non-independent and…

Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing, yet it poses unique challenges for Domain Generalization (DG), including strict privacy constraints, non-i.i.d. local…

This work investigates fault-resilient federated learning when the data samples are non-uniformly distributed across workers, and the number of faulty workers is unknown to the central server. In the presence of adversarially faulty workers…

This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training…

Federated Domain Adaptation (FDA) is a Federated Learning (FL) scenario where models are trained across multiple clients with unique data domains but a shared category space, without transmitting private data. The primary challenge in FDA…

Heterogeneity across devices in federated learning (FL) typically refers to statistical (e.g., non-i.i.d. data distributions) and resource (e.g., communication bandwidth) dimensions. In this paper, we focus on another important dimension…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

To address the problem of data inconsistencies among different facial expression recognition (FER) datasets, many cross-domain FER methods (CD-FERs) have been extensively devised in recent years. Although each declares to achieve superior…

Recent advances in CV and NLP have inspired researchers to develop general-purpose graph foundation models through pre-training across diverse domains. However, a fundamental challenge arises from the substantial differences in graph…

While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new…

Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model…

Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which…

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…

Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…

Naive joint training of large language models (LLMs) for multilingual preference alignment can suffer from negative interference. This is a known issue in multilingual training, where conflicting objectives degrade overall performance.…

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility…