arXiv:2606.00497v2 Announce Type: replace-cross Abstract: Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonom...
The paper introduces AURA, an LLM-powered mask‑reconstruct framework for anonymizing text while preserving utility. It decouples privacy localization from utility‑preserving reconstruction and uses adversarial checks to select candidates. Experiments on real‑user interview transcripts show that AURA achieves the lowest agentic re‑identification rates among non‑DP methods and retains more contextual utility than prior LLM anonymizers.
arXiv:2606. 27936v1 Announce Type: cross Abstract: The widespread collection of fine-grained location data by commercial data brokers creates a re-identification risk that is not widely recognised by the public.
The paper systematically studies how anonymizing input data affects large language models (LLMs). Five prominent LLMs were evaluated on eleven benchmarks, comparing performance on original versus pseudonymized inputs. Results show that anonymization generally degrades performance, with larger drops for more capable models and task-dependent effects; reversible anonymization preserves entity uniqueness better than irreversible redaction, and prompting about anonymization offers no benefit.
The paper introduces Veil-then-Reveal (VtR), a user-side framework that pseudo‑anonymizes personally identifiable information (PII) in prompts sent to large language models (LLMs) under a zero‑trust model. VtR replaces detected PII with realistic, same‑type surrogates using format‑preserving encryption for structured data and a keyed‑hash dictionary for semantic data, while preserving linguistic and structural cues. The system achieves high detection recall (97.9%), strong protection of detected values (95.2%), and near‑perfect round‑trip restoration (99.9%) across three datasets.
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.
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:2502. 17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks.
The paper evaluates TypeSafe AI’s Jev safety judge against GPT and GLM judges and local classifiers using a controlled adversarial test harness. Jev shows strong robustness on rule‑based tasks like input moderation, with minimal bypasses, but performs less well on judgment‑based tasks such as phishing detection, where it misses a higher proportion of phishing emails and is more prone to false positives. The study highlights Jev’s speed advantage and varying resilience depending on task type.
PrivacyFlow introduces a new benchmark, PrivacyBench, and a defense system that separates privacy planning from task execution in autonomous LLM agents. The system traces data provenance, models recipient knowledge, and simulates inference attacks to weigh disclosure risk against task utility, allowing it to minimize or block data sharing. Experiments show that PrivacyFlow reduces privacy failures and increases completed task sequences by 22–55 percentage points, while revealing a tradeoff between privacy, utility, and user autonomy.
arXiv:2607. 05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negotiate with services.