9 accepted papers
Federated Learning (FL) enables privacy-preserving distributed training but remains vulnerable to backdoor attacks. Attackers can embed malicious trigger-label associations into the global model by participating in the aggregation process. Existing defense methods typically defend against backdoor a
As large language models (LLMs) scale, their inference incurs substantial computational resources, exposing them to energy-latency attacks, where crafted prompts induce high energy and latency cost. Existing attack methods aim to prolong output by delaying the generation of termination symbols. Howe
Federated Graph Learning (FGL) has emerged as a compelling paradigm for collaboratively training a global model while preserving the privacy of multi-source graphs. Nonetheless, FGL faces a critical challenge of data heterogeneity, where semantic and structural discrepancies across clients significa
Vision-Language Pre-training (VLP) models, while achieving state-of-the-art performance on various multimodal tasks, exhibit significant vulnerability to multimodal adversarial examples. In black-box attack scenarios of VLP models, a key challenge lies in the limited transferability of these adversa
Backdoor attacks and adversarial attacks are two major security threats to deep neural networks (DNNs), with the former one is a training-time data poisoning attack that aims to implant backdoor triggers into models by injecting trigger patterns into training samples, and the latter one is a testing…
Data-free black-box attacks aim to attack a model without access to either the model parameters or training data. Existing methods use a generator to synthesize training samples and then train a substitute model to imitate the victim model. The adversarial examples (AEs) are finally generated using…
Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which…
As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasingly more popularity. While extensive studies have been devoted to improving the model accuracy on…
Recent research on edge-preserving image smoothing has suggested that bilateral filtering is vulnerable to maliciously perturbed filtering input. However, while most prior works analyze the adaptation of the range kernel in one-step manner, in this paper we take a more constructive view towards mult…