10 papers
Reliability Stress Testing of RAG Retrieval under Query-Relevant Corpus Poisoning
Janet Sung, Kainan Zhou, Gangzhen Qian +2
External text can affect a retrieval-augmented generation (RAG) system only after the retriever admits it to the model context. We stress this admission step while varying document…
Reference-based sensitivity analysis for bounded longitudinal outcomes
Divan Aristo Burger
Reference-based sensitivity analysis is widely used to assess departures from the assumption that data are missing at random in longitudinal randomized trials, but existing methods…
Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation
Gangzhen Qian, Kainan Zhou, Chuhong Xu +5
The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed.…
Bounded Provisional Visibility: Controlling Poisoning Exposure in Continuously Ingested RAG Vector Stores
Chuhong Xu, Lu Yi, Gangzhen Qian +3
Continuous ingestion can expose new retrieval-augmented generation (RAG) content to retrieval before vetting completes, creating a temporal attack surface that conventional admissi…
Protocol-Sensitive Evaluation of Log Anomaly Detection: Component Costs and Target-Access Sensitivity on HDFS and BGL
Hang Xiao, Janet Sung, Zhaoyi Li +2
Protocol choices can change the conclusions drawn from log anomaly detection benchmarks even when detector settings are fixed. We present a joint empirical study of split construct…
Claim-Gated Source-Risk Auditing for Generative Search
Kainan Zhou, Chuhong Xu, Gangzhen Qian +1
A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tu…
Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies
Hang Xiao, Chuhong Xu, Kainan Zhou +2
AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework covering 31 tasks and…
Query-Aware Source-Risk Triage for Retrieval-Augmented Generation
Kainan Zhou, Gangzhen Qian, Chuhong Xu +1
Retrieval-augmented generation (RAG) pipelines may omit a source's material relationship to the query. We study a pre-generation triage layer that treats this relationship as query…
IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives
Kainan Zhou, Gangzhen Qian, Zhaoyi Li +2
An external record may contain a procedure to apply or text to read, depending on the user's request. IBBench-Light tests both uses against the same record. Twelve semantic bases y…
Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families
Hang Xiao, Chuhong Xu, Kainan Zhou +2
Trust-Hub reuses host circuits: several files differ mainly in the inserted Trojan. When gates from sibling variants enter both training and test folds, a detector can benefit from…