Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models

• URL: http://arxiv.org/abs/2601.05076v1
• Date: Thu, 08 Jan 2026 16:19:43 GMT
• Title: Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models
• Authors: Arghyadeep Das, Sai Sreenivas Chintha, Rishiraj Girmal, Kinjal Pandey, Sharvi Endait,
• Abstract summary: Intermediate reasoning often leaks personally identifiable information (PII) even when final answers are sanitized.<n>We study how to induce privacy-first reasoning, where models reason without exposing sensitive information.<n>We show that private CoT reasoning can be achieved with minimal utility loss.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models (LRMs) improve performance, reliability, and interpretability by generating explicit chain-of-thought (CoT) reasoning, but this transparency introduces a serious privacy risk: intermediate reasoning often leaks personally identifiable information (PII) even when final answers are sanitized. We study how to induce privacy-first reasoning, where models reason without exposing sensitive information, using deployable interventions rather than post-hoc redaction. We introduce PII-CoT-Bench, a supervised dataset with privacy-aware CoT annotations, and a category-balanced evaluation benchmark covering realistic and adversarial leakage scenarios. Our results reveal a capability-dependent trend: state-of-the-art models benefit most from prompt-based controls, whereas weaker models require fine-tuning to achieve meaningful leakage reduction. Across models and categories, both approaches substantially reduce PII exposure with minimal degradation in utility, demonstrating that private reasoning can be achieved without sacrificing performance. Overall, we show that private CoT reasoning can be achieved with minimal utility loss, providing practical guidance for building privacy-preserving reasoning systems.

Related papers

• STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction [78.0692157478247]
  We propose STAR, a framework that bridges data-driven STatistical expectations with knowledge-driven Agentic Reasoning.<n>We show that STAR consistently outperforms all baselines on both score-based and rank-based metrics.
  arXiv  Detail & Related papers  (2026-02-12T16:30:07Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Does More Inference-Time Compute Really Help Robustness? [50.47666612618054]
  We show that small-scale, open-source models can benefit from inference-time scaling.<n>We identify an important security risk, intuitively motivated and empirically verified as an inverse scaling law.<n>We urge practitioners to carefully weigh these subtle trade-offs before applying inference-time scaling in security-sensitive, real-world applications.
  arXiv  Detail & Related papers  (2025-07-21T18:08:38Z)
• Leakage and Interpretability in Concept-Based Models [0.24466725954625887]
  Concept Bottleneck Models aim to improve interpretability by predicting high-level intermediate concepts.<n>They are known to suffer from information leakage, whereby models exploit unintended information encoded within the learned concepts.<n>We introduce an information-theoretic framework to rigorously characterise and quantify leakage.
  arXiv  Detail & Related papers  (2025-04-18T22:21:06Z)
• BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning [39.090104460303415]
  offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies.<n>This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data.<n>We introduce textbfBilintextbfEar textbfCAUSal rtextbfEpresentation(BECAUSE), an algorithm to capture causal representation for both states.
  arXiv  Detail & Related papers  (2024-07-15T17:59:23Z)
• Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort [31.992947353231564]
  Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors through human-understandable concepts. We propose a novel framework designed to exploit pre-trained models while being immune to these biases, thereby reducing vulnerability to spurious correlations. We evaluate the proposed method on multiple datasets, and the results demonstrate its effectiveness in reducing model reliance on spurious correlations while preserving its interpretability.
  arXiv  Detail & Related papers  (2024-07-12T03:07:28Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)

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.