PerceptFence: Content-Mediation Architecture and Deterministic Coverage for Screen-Share AI Assistants

arXiv:2609.34027 · cs.CR · Submitted 2026-09-27 · Read on arXiv

cs.CR

Submitted: 2026-09-27

Updated: 2026-10-05

Code: https://github.com/microsoft/presidi

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Robustness — 11× in this paper · explained in 5 episodes
• Consistency — 9× in this paper · explained in 3 episodes
• Core — 5× in this paper · explained in 2 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Adversarial Examples — 2× in this paper · explained in 2 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Text Anonymization Benchmark — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• LLM Integration — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
• Acceptability of AI Assistants for Privacy: Perceptions of Experts and Users on Personalized Privacy Assistants
• From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants
• Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• Prompt Injection attack against LLM-integrated Applications
• StruQ: Defending Against Prompt Injection with Structured Queries
• SecAlign: Defending Against Prompt Injection with Preference Optimization
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
• AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration
• Defeating Prompt Injections by Design
• Defending Against Indirect Prompt Injection Attacks With Spotlighting
• InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
• NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
• On Adaptive Attacks to Adversarial Example Defenses
• A Critical Evaluation of Defenses against Prompt Injection Attacks
• Formalizing and Benchmarking Prompt Injection Attacks and Defenses

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