GUIAuditor: Enabling Post-hoc Child Safety Forensics via Action-Guided GUI Provenance on Mobile Devices

arXiv:2609.28205 · cs.CR · Submitted 2026-09-23 · Read on arXiv

cs.CR

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/PKU-ASAL/GUIAuditor

Terminology

• Provenance — 62× in this paper · explained in 4 episodes
• Distillation — 20× in this paper · explained in 2 episodes
• Fidelity — 20× in this paper · explained in 2 episodes
• Accuracy — 19× in this paper · explained in 1 episode
• Core — 17× in this paper · explained in 2 episodes
• Human-in-the-Loop — 13× in this paper · explained in 3 episodes
• Adaptive Sampling — 6× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• F1 Score — 6× in this paper · explained in 3 episodes
• IEEE Symposium on Security and Privacy — 5× in this paper
• Multimodal Large Language Model — 5× in this paper
• Redundancy — 5× in this paper · explained in 2 episodes
• Sparsity — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Actor — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Explainability — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Mean Reciprocal Rank — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Accountability — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Institute for AI Industry Research — 1× in this paper
• Institutional Review Board — 1× in this paper
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Optical Character Recognition — 1× in this paper
• Quantization — 1× in this paper · explained in 12 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
• FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models
• UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats
• NODLINK: An Online System for Fine-Grained APT Attack Detection and Investigation
• Mobile GUI Agents under Real-world Threats: Are We There Yet?
• R3M: A Universal Visual Representation for Robot Manipulation
• Investigating Skin Temperature-Based Overheating in mmWave Smartphones Power and Thermal Models for Optimal Non-Throttling Performance
• LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
• AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
• TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone
• Play It Cool: Dynamic Shifting Prevents Thermal Throttling

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs