6 papers
Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
Zhaoxin Wang, Handing Wang, Cong Tian +1
Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attac…
Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric
Hao Chen, Cong Tian, Zixuan He +3
With the significant success achieved by large language models (LLMs) like LLaMA, edge computing-based LLM inference services for mobile and PC are in high demand for data privacy.…
Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
Zhaoxin Wang, Handing Wang, Cong Tian +1
Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak at…
Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
Jiangtao Liu, Zhaoxin Wang, Handing Wang +2
Text-to-Image (T2I) generation has advanced rapidly in recent years, but they also raise safety concerns due to the potential production of harmful content. In the practical deploy…
Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
Zhaoxin Wang, Handing Wang, Cong Tian +1
Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT…
Dual sparse training framework: inducing activation map sparsity via Transformed regularization
Xiaolong Yu, Cong Tian
Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational a…