activity
20242026
most citedBackdoor Attacks against Hybrid Classical-Quantum Neural Networks

2 citations · 3 across the 9 of their papers we have counts for

collaborators

11 papers

cs.CR2026

RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services

Zihan Wang, Boheng Li, Rui Zhang +5

Diffusion-based text-to-image (T2I) models are increasingly used for visual content creation, making their generation capability a valuable intellectual property asset. However, th…

cs.CR2026

DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging

Jiayang Zhang, Ji Guo, Jiachen Li +2

Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitiga…

cs.CR2026

EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation

Xi Nie, Hongwei Li, Shenghao Wu +3

Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fundamental challenge in dynamic a…

cs.CR2026

InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

Jian Xiong, Wenbo Jiang, Zihan Wang +4

Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a pu…

cs.LG2026

UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding

Jiaming He, Fuming Luo, Hongwei Li +5

Unlearnable examples (UE) have emerged as a practical mechanism to prevent unauthorized model training on private vision data, while extending this protection to tabular data is no…

cs.CR2025

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models

Zihan Wang, Rui Zhang, Hongwei Li +4

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods,…