7 citations · 15 across the 18 of their papers we have counts for
5 papers · 1 filter
Provably Secure Robust Image Steganography via Cross-Modal Error Correction
Yuang Qi, Kejiang Chen, Na Zhao +2
The rapid development of image generation models has facilitated the widespread dissemination of generated images on social networks, creating favorable conditions for provably sec…
On the Vulnerability of Text Sanitization
Meng Tong, Kejiang Chen, Xiaojian Yuan +4
Text sanitization, which employs differential privacy to replace sensitive tokens with new ones, represents a significant technique for privacy protection. Typically, its performan…
A Closer Look at Machine Unlearning for Large Language Models
Xiaojian Yuan, Tianyu Pang, Chao Du +3
Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt…
Natias: Neuron Attribution based Transferable Image Adversarial Steganography
Zexin Fan, Kejiang Chen, Kai Zeng +3
Image steganography is a technique to conceal secret messages within digital images. Steganalysis, on the contrary, aims to detect the presence of secret messages within images. Re…
Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
Jiawei Zhao, Kejiang Chen, Xiaojian Yuan +1
In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerabl…