Impact

Data security Research

Issues affecting data confidentiality and integrity

3 matching entries out of 171 in this category

Data security research results

3 entries

PII leakage in document-image redaction benchmarks

Published Sep 2, 2026Analyzed Sep 9, 2026Source: arXiv

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

GLiNER-base
GLiNER-multi-PII
NVIDIA GLiNER PII
GLiNER2
Qwen3-VL-32B
InternVL3 38B
GPT-5.4
GPT-5.5

Voice Agent Behavioral Bypass

Published Feb 7, 2026Analyzed Feb 21, 2026Source: arXiv

Audio Large Language Models (ALLMs) integrated into voice agent systems for high-stakes domains (banking, IT support, logistics) are vulnerable to multimodal adversarial attacks via spoken interaction. Adversaries can exploit the model's inherent compliance and contextual awareness through multi-turn dialogue to bypass authentication safeguards, escalate privileges (e.g., unauthorized credit limit increases), exfiltrate sensitive Personally Identifiable Information (PII), and poison…

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

Evaluated models: GPT-4o, GPT-4o Mini, Gemini 1.5 Pro+4 more

GPT-4o
GPT-4o Mini
Gemini 1.5 Pro
Gemini 2.5 Flash
Gemini 2.5 Pro
Qwen2-Audio 7B
Qwen 2.5 Omni 7B

Flowchart-based LVLM Jailbreak Attack

Published Feb 28, 2025Analyzed Mar 19, 2025Source: arXiv

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

Claude 3.5 Sonnet 20240620
Gemini 1.5 Flash
GPT-4o 2024-08-06
GPT-4o Mini 2024-07-18
InternVL2.5 8B
LLaVA NeXT 8B
Qwen2-VL 7B Instruct

Related research categories