SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2603.17292v1
• Date: Wed, 18 Mar 2026 02:40:54 GMT
• Title: SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generation
• Abstract summary: SEAL-Tag is a runtime environment that protects Personally Identifiable Information (PII)<n> SEAL-Tag introduces the SEAL-Probe protocol, transforming auditing into a structured tool-use operation where the model generates a verifiable PII-Evidence Table (PET) alongside its draft.<n>To overcome the privacy "Cold Start" problem, we introduce the S0--S6 Anchored Synthesis Pipeline, generating high-fidelity, provenanced RAG interactions.
• Score: 36.47163805456756
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) systems introduce a critical vulnerability: contextual leakage, where adversaries exploit instruction-following to exfiltrate Personally Identifiable Information (PII) via adaptive extraction. Current defenses force a rigid trade-off between semantic utility and latency. We present SEAL-Tag, a privacy-preserving runtime environment that resolves this via a Verify-then-Route paradigm. SEAL-Tag introduces the SEAL-Probe protocol, transforming auditing into a structured tool-use operation where the model generates a verifiable PII-Evidence Table (PET) alongside its draft. To adjudicate this evidence, we employ a Probabilistic Circuit (PC) that enforces verifiable logical constraints for robust decision-making. To overcome the privacy "Cold Start" problem, we introduce the S0--S6 Anchored Synthesis Pipeline, generating high-fidelity, provenanced RAG interactions. We pair this with a Two-Stage Curriculum that first optimizes for entity detection before aligning the model to the rigorous audit protocol. Our evaluation demonstrates that SEAL-Tag establishes a new Pareto frontier, reducing adaptive leakage by over 8$\times$ while matching the utility and speed of unsafe baselines.

Related papers

• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection [23.7834497390662]
  SAFESEAL is a novel key-conditioned watermarking framework that achieves strong detectability with minimal impact on model utility.<n>We show that SAFESEAL outperforms baselines in utility, detectability, and robustness, achieving a BERTScore of 0.983, entity similarity of 0.963, a 98.2% detection rate, and the highest human ratings for text quality and content, with latency comparable to the fastest baseline.
  arXiv  Detail & Related papers  (2026-05-22T02:51:42Z)
• Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference [3.3323431541048385]
  We present a verification framework and protocol that replaces full proofs with a lightweight, sampling-based approach.<n>We formalize the conditions under which trace separation between functionally dissimilar models can be leveraged to argue the security of verifiable inference protocols.<n>Our approach reduces proving times by several orders of magnitude compared to state-of-the-art cryptographic proof systems.
  arXiv  Detail & Related papers  (2026-03-19T15:24:27Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• Detecting Sleeper Agents in Large Language Models via Semantic Drift Analysis [0.0]
  Large Language Models (LLMs) can be backdoored to exhibit malicious behavior under specific deployment conditions.<n>Recent work by Hubinger et al. demonstrated that backdoors persist through safety training, yet no practical detection methods exist.<n>We present a novel dual-method detection system combining semantic drift analysis with canary baseline comparison.
  arXiv  Detail & Related papers  (2025-11-20T02:42:41Z)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking [58.475471437150674]
  We propose sequential watermarking for soft prompts (SWAP)<n>SWAP encodes watermarks through a specific order of defender-specified out-of-distribution classes.<n>Experiments on 11 datasets demonstrate SWAP's effectiveness, harmlessness, and robustness against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-11-05T13:48:48Z)
• Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations [0.3805935148497361]
  We introduce Model-Bound Latent Exchange (MoBLE), a decoder-binding property in Transformer autoencoders formalized as Zero-Shot Decoder Non-Transferability (ZSDN)<n>In identity tasks using iso-architectural models trained on identical data but differing in seeds, self-decoding achieves more than 0.91 exact match and 0.98 token accuracy, while zero-shot cross-decoding collapses to chance without exact matches.<n>MoBLE offers a lightweight, accelerator-friendly approach to secure AI deployment in safety-critical domains, including aviation and cyber-physical systems.
  arXiv  Detail & Related papers  (2025-11-02T15:29:44Z)
• HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention [0.0]
  HALT-RAG is a post-hoc verification system designed to identify hallucinations in the outputs of Retrieval-Augmented Generation pipelines.<n>Our flexible and task-adaptable framework uses a universal feature set derived from an ensemble of two frozen, off-the-shelf Natural Language Inference (NLI) models and lightweight lexical signals.<n>By pairing our universal feature set with a lightweight, task-adapted and a precision-constrained decision policy, HALT-RAG achieves strong OOF F1-scores of 0.7756, 0.9786, and 0.7391 on the summarization, QA, and dialogue
  arXiv  Detail & Related papers  (2025-09-09T07:58:46Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.