arXiv:2606. 16175v1 Announce Type: new Abstract: Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events.
arXiv:2606. 09865v1 Announce Type: new Abstract: Privacy and data sharing are often in tension.
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.
Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because restrictions propagate through derivations, summaries can conceal private, poisoned, untrusted, or revoked sources, enabling unauthorized reads or unsafe actions.
arXiv:2608. 10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action.
The paper proposes a generation‑provenance substrate for synthetic speech research objects, binding source specifications, generated content, waveform, target, fact requirements, quality signals, review lineage, and an immutable manifest identity. It audits this substrate in a private Japanese care‑handoff pipeline, documenting 113 assets and 1.552 hours of synthetic speech with linked audio, transcripts, notes, and fact checklists, while noting selective human evidence and source‑specific gaps. The authors argue that provenance is necessary but not sufficient for behavior attribution, requiring additional frozen training runs and intervention evidence, and they provide a compact provenance contract, audit protocol, and a bounded case study. "whyItMatters":"The study highlights the need for detailed provenance records to enable reliable auditing and attribution of synthetic data behavior, underscoring limitations in current practices and offering a structured framework for future research."
GraphProfiler is an auditable LLM-based profiler that infers sensitive attributes such as age, income, and occupation from user-generated content by aggregating indirect cues across many posts. It represents each user's post history as a source-linked personal knowledge graph, allowing predictions to be traced back to specific posts, concepts, and relationships. The system achieves an 86.7% success rate on the SynthPAI benchmark and 84.6% on PANDORA, citing supporting evidence for over 98% of predictions and demonstrating that cited posts significantly contribute to attack success.
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.
arXiv:2606. 04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, environments, and other agents.
arXiv:2607. 15606v1 Announce Type: new Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing, yet a generator can reproduce every marginal and every foreign-key relationship while emitting timestamps that run backwards or repeat, and while sending entities along paths that no real entity followed.
ReCoPII is a relation‑grounded framework that generates contextual PII masking datasets without assuming a single data subject. It constructs ontology‑constrained entity relations, writes insertion sentences with placeholders, and derives MASK/KEEP labels through automated annotation and LLM verification. Applied to Korean documents across six domains, ReCoPII‑Ko achieves high agreement with human annotators (88.42% on KEEP labels) and improves masking performance compared to SPY‑style augmentation.
arXiv:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and int...