collaborators

15 papers

cs.CR2026

Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation

Yanhang Li, Zhichao Fan, Zexin Zhuang

Black-box privacy scores for retrieval-augmented generation (RAG) are difficult to interpret unless the audited defense's active pipeline hook is known. We propose an active-path a…

cs.SE2026

The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines

Zhichao Fan, Yanhang Li, Zexin Zhuang +2

Trust-benchmark scores reported on a chat-LLM release line are often carried across several checkpoints of the same line, as if the underlying model had not shifted between release…

cs.LG2026

Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits

Yanhang Li, Zhichao Fan, Zexin Zhuang

Governance frameworks ask AI providers and auditors for documented evaluation evidence, and perturbation-based construct-validity audits are a common form of that evidence. We argu…

cs.LG2026

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

Yingshuo Wang, Xian Sun, Lingdong Kong +4

Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-st…

cs.CR2026

Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed

Zhichao Fan, Zexin Zhuang, Yanhang Li

We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.5-VL-7B canary testbed and report three post-hoc cases where it disagrees with full-span secret NLL or…

cs.LG2026

Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees

Yingshuo Wang, Xian Sun, Yanhang Li +2

Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increa…