Related papers: ModelForge: Using GenAI to Improve the Development…
Enrich-by-need protocol analysis is a style of symbolic protocol analysis that characterizes all executions of a protocol that extend a given scenario. In effect, it computes a strongest security goal the protocol achieves in that scenario.…
Recent work has shown that integrating large language models (LLMs) with theorem provers (TPs) in neuro-symbolic pipelines helps with entailment verification and proof-guided refinement of explanations for natural language inference (NLI).…
Large language models (LLMs) have demonstrated impressive performance on natural language tasks, but their decision-making processes remain largely opaque. Existing explanation methods either suffer from limited faithfulness to the model's…
Metamorphic Relations (MRs) serve as a foundational mechanism for generating semantically equivalent mutations. Software engineering has advanced significantly in recent years with the advent of Large Language Models (LLMs). However, the…
We propose a methodology for verifying security properties of network protocols at design level. It can be separated in two main parts: context and requirements analysis and informal verification; and formal representation and procedural…
Answer Set Programming (ASP) is a popular declarative programming language for solving hard combinatorial problems. Although ASP has gained widespread acceptance in academic and industrial contexts, there are certain user groups who may…
We present a novel framework that integrates Large Language Models (LLMs) with automated planning and formal verification to streamline the creation and use of Markov Decision Processes (MDP). Our system leverages LLMs to extract structured…
In industrial model-based development (MBD) frameworks, requirements are typically specified informally using textual descriptions. To enable the application of formal methods, these specifications need to be formalized in the input…
Our goal is to use formal methods to analyse normative documents written in English, such as privacy policies and service-level agreements. This requires the combination of a number of different elements, including information extraction…
In the paper we introduce a process model of security protocols, where processes are graphs with edges labelled by actions, and present a new method of specification and verification of security protocols based on this model.
Optimizing compilers are essential for the efficient and correct execution of software across various scientific fields. Domain-specific languages (DSL) typically use higher level intermediate representations (IR) in their compiler…
Formal verification techniques are widely used for detecting design flaws in software systems. Formal verification can be done by transforming an already implemented source code to a formal model and attempting to prove certain properties…
Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…
Despite rapid progress in logic locking (LL), reproducibility remains a challenge as codes are rarely made public. We present LockForge, a first-of-its-kind, multi-agent large language model (LLM) framework that turns LL descriptions in…
With the rapid advancement of artificial intelligence-generated content (AIGC) technologies, including multimodal large language models (MLLMs) and diffusion models, image generation and manipulation have become remarkably effortless.…
Feature attribution methods, such as SHAP and LIME, explain machine learning model predictions by quantifying the influence of each input component. When applying feature attributions to explain language models, a basic question is defining…
Simulation has become an essential component of designing and developing scientific experiments. The conventional procedural approach to coding simulations of complex experiments is often error-prone, hard to interpret, and inflexible,…
Characterizing the computational power of neural network architectures in terms of formal language theory remains a crucial line of research, as it describes lower and upper bounds on the reasoning capabilities of modern AI. However, when…
The ability to automatically generate accurate protocols for scientific experiments would represent a major step towards the automation of science. Large Language Models (LLMs) have impressive capabilities on a wide range of tasks, such as…
Current approaches for formal verification of algorithms face important limitations. For specification, they cannot express algorithms naturally and concisely, especially for algorithms with states and flexible control flow. For…