Hugging Face Trending Papers
Privacy Washing: Detecting Internal Contradictions in Privacy Policies
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computation and Language
Sep 3
Privacy Washing: Detecting Internal Contradictions in Privacy Policies
The study introduces a four‑stage pipeline to detect internal contradictions—termed privacy washing—in privacy policies. Applied to two corpora (123 policies from 2026 and 115 from 2015), the pipeline identifies contradictions in 12.2% of the newer policies and 36.5% of the older ones, with third‑party sharing conflicts being the most common. A stability re‑run confirms similar prevalence rates and shows that the majority of contradictions are consistent across different model configurations.
arXiv AI
Jul 10
When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals
arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.
arXiv AI
Aug 18
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
arXiv Computer Vision
Sep 14
BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
arXiv AI
Aug 11
PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
arXiv:2608. 09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints.
arXiv AI
Jun 10
IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts
arXiv:2606. 09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation.