Noninterference Analysis of Reversible Systems: An Approach Based on Branching Bisimilarity

• URL: http://arxiv.org/abs/2311.15670v4
• Date: Tue, 21 Jan 2025 16:04:04 GMT
• Title: Noninterference Analysis of Reversible Systems: An Approach Based on Branching Bisimilarity
• Authors: Andrea Esposito, Alessandro Aldini, Marco Bernardo, Sabina Rossi,
• Abstract summary: Classical equivalence-based approaches to noninterference mainly rely on weak bisimulation semantics. We show that this approach is not sufficient to identify potential covert channels in the presence of reversible computations. To capture the effects of back-and-forth computations, it is necessary to switch to a more expressive semantics.
• Score: 41.94295877935867
• License:
• Abstract: The theory of noninterference supports the analysis of information leakage and the execution of secure computations in multi-level security systems. Classical equivalence-based approaches to noninterference mainly rely on weak bisimulation semantics. We show that this approach is not sufficient to identify potential covert channels in the presence of reversible computations. As illustrated via a database management system example, the activation of backward computations may trigger information flows that are not observable when proceeding in the standard forward direction. To capture the effects of back-and-forth computations, it is necessary to switch to a more expressive semantics, which has been proven to be branching bisimilarity in a previous work by De Nicola, Montanari, and Vaandrager. In this paper we investigate a taxonomy of noninterference properties based on branching bisimilarity along with their preservation and compositionality features, then we compare it with the taxonomy of Focardi and Gorrieri based on weak bisimilarity.

Related papers

• Noninterference Analysis of Irreversible or Reversible Systems with Nondeterminism and Probabilities [44.99833362998488]
  Noninterference theory supports the analysis of secure computations in multi-level security systems. In a nondeterministic setting, assessing noninterference through weak bisimilarity is adequate for irreversible systems, whereas for reversible ones branching bisimilarity has been proven to be more appropriate. We recast noninterference properties by adopting probabilistic variants of weak and branching bisimilarities for irreversible and reversible systems respectively.
  arXiv  Detail & Related papers  (2025-01-31T16:49:42Z)
• Post-hoc Probabilistic Vision-Language Models [51.12284891724463]
  Vision-language models (VLMs) have found remarkable success in classification, retrieval, and generative tasks. We propose post-hoc uncertainty estimation in VLMs that does not require additional training. Our results show promise for safety-critical applications of large-scale models.
  arXiv  Detail & Related papers  (2024-12-08T18:16:13Z)
• Data-Driven Reachability Analysis of Stochastic Dynamical Systems with Conformal Inference [1.446438366123305]
  We consider data-driven reachability analysis of discrete-time dynamical systems using conformal inference. We focus on learning-enabled control systems with complex closed-loop dynamics.
  arXiv  Detail & Related papers  (2023-09-17T07:23:01Z)
• 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)
• Causal Inference via Style Transfer for Out-of-distribution Generalisation [10.998592702137858]
  Out-of-distribution generalisation aims to build a model that can generalise well on an unseen target domain. We propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment.
  arXiv  Detail & Related papers  (2022-12-06T15:43:54Z)
• Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems [16.065867388984078]
  Binary perceptron is a model of supervised learning for the non- algorithmic optimization. We show that the instability for breaking the replica saddle point is identical to the free energy function.
  arXiv  Detail & Related papers  (2021-11-26T03:23:18Z)
• Uncertainty-Aware Few-Shot Image Classification [118.72423376789062]
  Few-shot image classification learns to recognize new categories from limited labelled data. We propose Uncertainty-Aware Few-Shot framework for image classification.
  arXiv  Detail & Related papers  (2020-10-09T12:26:27Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)
• Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights [16.538973310830414]
  A desirable class of priors would represent weights compactly, capture correlations between weights, and allow inclusion of prior knowledge. This paper introduces two innovations: (i) a process-based hierarchical model for network weights based on unit embeddings that can flexibly encode correlated weight structures, and (ii) input-dependent versions of these weight priors that can provide convenient ways to regularize the function space. We show these models provide desirable test-time uncertainty estimates on out-of-distribution data, demonstrate cases of modeling inductive biases for neural networks with kernels, and demonstrate competitive predictive performance on an active learning benchmark
  arXiv  Detail & Related papers  (2020-02-10T07:19:52Z)

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.