What You See Is Not What AI Gets: DPAgent-in-the-Middle Defense Against AI-Groomed Deceptive Patterns
cs.CR
Submitted: 2026-06-05
Updated: 2026-09-08
Project page: https://www.similarweb.com/top-websites
License: http://creativecommons.org/licenses/by/4.0/
The gist: Privacy deceptive patterns in web interfaces manipulate users into disclosing personal data, yet existing defenses are fragmented, static, and increasingly vulnerable to manipulation by large
Terminology
Abstract
Privacy deceptive patterns in web interfaces manipulate users into disclosing personal data, yet existing defenses are fragmented, static, and increasingly vulnerable to manipulation by large language models. Moreover, data voids, areas of information scarcity on the web, allow adversaries to inject misleading content that can be scraped and learned by AI systems, amplifying both deceptive design and model misbehavior. In this paper, we formalize AI grooming as a new threat in which adversaries seed benign-looking artifacts carrying machine-consumable manipulative signals into AI-mediated workflows. To address this threat, we present DPAgent, an agentic, reasoning-aware framework that orchestrates four specialized agents combining latent-space purification with defensive prompting to explore, detect, and repair privacy deceptive interfaces in live web environments. Extensive evaluations show that DPAgent filters 91% of naive whole-page generated samples and consistently reduces attack success across five targeted grooming strategies, achieves state-of-the-art detection with a micro F1 of 0.82, explores over 80% of pattern types while visiting only about 10% of the pages required by baselines, and successfully repairs 89.7% of correctly detected PDP instances. Our results demonstrate the promise of agent-in-the-middle defenses for securing the web UI supply chain against deceptive design and emerging AI threats rooted in data void exploitation.
Sources
- Detecting Adversarial Samples from Artifacts
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
- Proximal Policy Optimization Algorithms
- WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
- The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
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