Data security Research

Issues affecting data confidentiality and integrity

2 matching entries out of 171 in this category

Data security research results

2 entries

PII leakage in document-image redaction benchmarks

Published 9/2/2026

Analyzed 9/9/2026

Document-image PII detection can miss identifiers despite improving average localization scores. LeakageBench evaluates 500 pages with 11,954 annotations.

LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images

Evaluated models: GLiNER-base, GLiNER-multi-PII, NVIDIA GLiNER PII +5 more

Source: arXiv

Flowchart-based LVLM Jailbreak Attack

Published 2/1/2025

Analyzed 3/19/2025

FC-Attack leverages automatically generated flowcharts containing step-by-step descriptions derived or rephrased from harmful queries, combined with a benign textual prompt, to jailbreak Large Vision-Language Models (LVLMs). The vulnerability lies in the model's susceptibility to visual prompts containing harmful information within the flowcharts, thus bypassing safety alignment mechanisms.

FC-Attack: Jailbreaking Large Vision-Language Models via Auto-Generated Flowcharts

Evaluated models: Claude 3.5 Sonnet 20240620, Gemini 1.5 Flash, GPT-4o 2024-08-06 +4 more

Source: arXiv

Related research categories