activity
20242026
most citedAn LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

9 citations · 10 across the 6 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.CR2025

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Hanbin Hong, Shuang Wu, Shuya Feng +6

Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends on the target mode…

cs.CR2025

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

Nima Naderloui, Shenao Yan, Binghui Wang +4

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning en…