From the 1 of 5 linked papers with an AI index.
5 papers
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…
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
Zhiyang Dai, Yansong Gao, Boyu Kuang +5
Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet d…
ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
Yongqi Jiang, Yansong Gao, Boyu Kuang +3
Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurrently satisfy the following tw…
Empowering IoT Firmware Secure Update with Customization Rights
Weihao Chen, Yansong Gao, Boyu Kuang +3
Firmware updates remain the primary line of defense for IoT devices; however, the update channel itself has become a well-established attack vector. Existing defenses mainly focus…
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…