activity
20222026
most citedCracking White-box DNN Watermarks via Invariant Neuron Transforms

2 citations · 2 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CL2026

From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models

Wenxuan Li, Zhenfei Zhang, Mi Zhang +4

Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential reme…

cs.CV2026

SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers

Xiang Yang, Feifei Li, Mi Zhang +3

Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when…

cs.CR2026

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

Pei Chen, Geng Hong, Xinyi Wu +6

The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summari…

cs.CV2025

3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition

Yuanmin Huang, Wenxuan Li, Mi Zhang +3

Deep neural networks have recently achieved notable progress in 3D point cloud recognition, yet their vulnerability to adversarial perturbations poses critical security challenges…

cs.LG2025

Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain

Yuanmin Huang, Mi Zhang, Zhaoxiang Wang +2

Time series classification (TSC) is a cornerstone of modern web applications, powering tasks such as financial data analysis, network traffic monitoring, and user behavior analysis…

cs.CR2024

Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding

Huming Qiu, Guanxu Chen, Mi Zhang +3

In recent years, text-to-image (T2I) generation models have made significant progress in generating high-quality images that align with text descriptions. However, these models als…