Related papers: Sheaf semantics of termination-insensitive noninte…
Large language models suffer from "hallucinations"-logical inconsistencies induced by semantic noise. We propose that current architectures operate in a "Metric Phase," where causal order is vulnerable to spontaneous symmetry breaking.…
We show how security type systems from the literature of language-based noninterference can be represented more directly as predicates defined by structural recursion on the programs. In this context, we show how our uniform syntactic…
We propose a constraint-based flow-sensitive static analysis for concurrent programs by iteratively composing thread-modular abstract interpreters via the use of a system of lightweight constraints. Our method is compositional in that it…
Bounded linear types have proved to be useful for automated resource analysis and control in functional programming languages. In this paper we introduce an affine bounded linear typing discipline on a general notion of resource which can…
The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$…
Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…
Semantic similarity based retrieval is playing an increasingly important role in many IR systems such as modern web search, question-answering, similar document retrieval etc. Improvements in retrieval of semantically similar content are…
Neural network inference typically operates on raw input data, increasing the risk of exposure during preprocessing and inference. Moreover, neural architectures lack efficient built-in mechanisms for directly authenticating input data.…
A syntactic model is presented for the specification of finite-state synchronous digital logic systems with complex input/output interfaces, which control the flow of data between opaque computational elements, and for the composition of…
For natural language understanding tasks, either machine reading comprehension or natural language inference, both semantics-aware and inference are favorable features of the concerned modeling for better understanding performance. Thus we…
Security of information flow is commonly understood as preventing any information leakage, regardless of how grave or harmless consequences the leakage can have. In this work, we suggest that information security is not a goal in itself,…
Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-relevant information and reduce model interpretability. This work proposes a semantic feature…
Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opaque, with existing approaches often sacrificing semantic…
This paper focuses on a fundamental problem on information security of bounded labeled Petri nets: non-interference analysis. As in hierarchical control, we assume that a system is observed by users at different levels, namely high-level…
Phase field modelling offers an extremely general framework to predict microstructural evolutions in complex systems. However, its computational implementation requires a discretisation scheme with a grid spacing small enough to preserve…
In this paper, we focus on the synthesis of secure timed systems which are modelled as timed automata. The security property that the system must satisfy is a non-interference property. Intuitively, non-interference ensures the absence of…
The rise of serverless computing provides an opportunity to rethink cloud security. We present an approach for securing serverless systems using a novel form of dynamic information flow control (IFC). We show that in serverless…
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a treebank during training, through a…
Membrane particles such as proteins and lipids organize into zones that perform unique functions. Here, I introduce a topological and category-theoretic framework to represent particle and zone intra-scale interactions and inter-scale…
Privacy-preserving process mining enables the analysis of business processes using event logs, while giving guarantees on the protection of sensitive information on process stakeholders. To this end, existing approaches add noise to the…