9 papers
Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks
Xiaoyan Feng, Yanjun Zhang, He Zhang +2
Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness allows an adver…
ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
Zirui Gong, Leo Yu Zhang, Yanjun Zhang +4
Federated Learning (FL) enables collaborative model training by sharing model updates instead of raw data, aiming to protect user privacy. However, recent studies reveal that these…
Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
Di Mi, Yanjun Zhang, Leo Yu Zhang +4
Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a se…
Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
Xiaomei Zhang, Zhaoxi Zhang, Leo Yu Zhang +3
Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-…
TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening
Nam Le, Leo Yu Zhang, Kewen Liao +2
As deep neural networks power increasingly critical applications, stealthy backdoor attacks, where poisoned training inputs trigger malicious model behaviour while appearing benign…
Character-Level Perturbations Disrupt LLM Watermarks
Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang +5
Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evalua…