6 papers
LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets
Shixin Guo, Ming Zhong, Xuhong Zhang +5
Generating high-quality adversarial texts with low query budgets remains a challenging problem in the hard-label scenario. Most existing approaches rely on greedy algorithms, where…
An Inversion-based Measure of Memorization for Diffusion Models
Zhe Ma, Qingming Li, Xuhong Zhang +5
The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are susceptible to training data…
PRSA: Prompt Stealing Attacks against Real-World Prompt Services
Yong Yang, Changjiang Li, Qingming Li +6
Recently, large language models (LLMs) have garnered widespread attention for their exceptional capabilities. Prompts are central to the functionality and performance of LLMs, maki…
FaceSwapGuard: Safeguarding Facial Privacy from DeepFake Threats through Identity Obfuscation
Li Wang, Zheng Li, Xuhong Zhang +2
DeepFakes pose a significant threat to our society. One representative DeepFake application is face-swapping, which replaces the identity in a facial image with that of a victim. A…
Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
Tong Ye, Yangkai Du, Tengfei Ma +4
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating code. However, the misuse of LLM-generated (synthetic) code has raised concerns in both educatio…
FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning
Zhenyu Wen, Wanglei Feng, Di Wu +6
Federated Learning (FL), as a mainstream privacy-preserving machine learning paradigm, offers promising solutions for privacy-critical domains such as healthcare and finance. Altho…