35 citations · 64 across the 38 of their papers we have counts for
15 papers · 1 filter
Data Free Backdoor Attacks
Bochuan Cao, Jinyuan Jia, Chuxuan Hu +5
Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing ba…
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Yaopei Zeng, Yuanpu Cao, Bochuan Cao +3
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation o…
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
Jiaqi Wang, Xiaochen Wang, Lingjuan Lyu +2
This study introduces the Federated Medical Knowledge Injection (FEDMEKI) platform, a new benchmark designed to address the unique challenges of integrating medical knowledge into…
Adversarially Robust Industrial Anomaly Detection Through Diffusion Model
Yuanpu Cao, Lu Lin, Jinghui Chen
Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not…
FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models
Xiaochen Wang, Jiaqi Wang, Houping Xiao +2
Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are hi…
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Yuanpu Cao, Tianrong Zhang, Bochuan Cao +4
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning see…
FADAS: Towards Federated Adaptive Asynchronous Optimization
Yujia Wang, Shiqiang Wang, Songtao Lu +1
Federated learning (FL) has emerged as a widely adopted training paradigm for privacy-preserving machine learning. While the SGD-based FL algorithms have demonstrated considerable…
Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
Changjiang Li, Ren Pang, Bochuan Cao +4
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifyi…
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
Tianrong Zhang, Zhaohan Xi, Ting Wang +2
Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well…
Graph Adversarial Diffusion Convolution
Songtao Liu, Jinghui Chen, Tianfan Fu +3
This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing…
PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
Jooyoung Lee, Toshini Agrawal, Adaku Uchendu +3
Recent studies have raised concerns about the potential threats large language models (LLMs) pose to academic integrity and copyright protection. Yet, their investigation is predom…
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
Tianrong Zhang, Bochuan Cao, Yuanpu Cao +3
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mountin…
JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
Yurui Chang, Bochuan Cao, Yujia Wang +2
Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content stil…
Backdoor Contrastive Learning via Bi-level Trigger Optimization
Weiyu Sun, Xinyu Zhang, Hao Lu +4
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnera…
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
Ziyi Yin, Muchao Ye, Tianrong Zhang +5
Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significa…