Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
The More It Says, the More You Pay: A Black-Box Audit of Provider-Side Token Inflation in LLM Services
Leilei Chen, Lan Zhang, Chen Tang +5
In pay-per-token LLM services, the more a model says, the more users pay. Dishonest providers can covertly manipulate generation to inflate output tokens while largely preserving t…
cs.CR2026
Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
Pengcheng Sun, Lan Zhang, Zhaopeng Zhang +2
Large language models (LLMs) are increasingly deployed in enterprise settings where they handle sensitive documents and user context, raising acute concerns over security and contr…
cs.CR2025
Untraceable DeepFakes via Traceable Fingerprint Elimination
Jiewei Lai, Lan Zhang, Chen Tang +3
Recent advancements in DeepFakes attribution technologies have significantly enhanced forensic capabilities, enabling the extraction of traces left by generative models (GMs) in im…