works on

From the 1 of 5 linked papers with an AI index.

activity
20242026
collaborators

5 papers

cs.CR2026

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

Na Li, Boyu Kuang, Hongsheng Hu +4

The paper shows that mixing text‑to‑image synthetic data with real data during training can increase privacy leakage of the real samples, and introduces a method (RSMixLeak) to mea…

cs.CR2026

From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure

Qirui Huang, Na Li, Hongsheng Hu +3

To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age es…

cs.CR2025

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Na Li, Yansong Gao, Hongsheng Hu +2

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning (DL) models, including recent foundation models like large language models (L…

cs.CR2025

From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints

Yansong Gao, Huaibing Peng, Hua Ma +5

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all…

cs.CR2024

Intellectual Property Protection for Deep Learning Model and Dataset Intelligence

Yongqi Jiang, Yansong Gao, Chunyi Zhou +3

With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significan…