Related papers: Formal Modeling and SMT-Based Parameterized Verifi…
Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, this multi-class setting, which exclusively uses normal data,…
Due to the limitations of SCADE models in expressing and verifying abstract specifications in safety-critical systems, this study proposes a formal verification framework based on the B-Method. By establishing a semantic equivalence…
We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive…
Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing…
When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a local checkpoint is efficient but can leave committed downstream work tied to an upstream…
This paper investigates the problem of Secure Multi-party Batch Matrix Multiplication (SMBMM), where a user aims to compute the pairwise products…
In this work we develop a fully automatic verification procedure of safety properties of Scade programs. We transform each such program into an SMT instance (Satisfiability Modulo Theories) and feed this to a solver. The goal is to have a…
Correct operation of many critical systems is dependent on the data consistency and integrity properties of underlying databases. Therefore, a verifiable and rigorous database design process is highly desirable. This research aims to…
We examine Memory Networks for the task of question answering (QA), under common real world scenario where training examples are scarce and under weakly supervised scenario, that is only extrinsic labels are available for training. We…
Designing correct replicated data types (RDTs) is challenging because replicas evolve independently and must be merged while preserving application intent. A promising approach is correct-by-construction development in a proof-oriented…
Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sensitive to a specified…
Malware presents a persistent threat to user privacy and data integrity. To combat this, machine learning-based (ML-based) malware detection (MD) systems have been developed. However, these systems have increasingly been attacked in recent…
Constraint solving is an elementary way for verification of deep neural networks (DNN). In the domain of AI safety, a DNN might be modified in its structure and parameters for its repair or attack. For such situations, we propose the…
Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing…
Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…
Markov decision processes model systems subject to nondeterministic and probabilistic uncertainty. A plethora of verification techniques addresses variations of reachability properties, such as: Is there a scheduler resolving the…
The design of business processes involves the usage of modeling languages, tools and methodologies. In this paper we highlight and address a relevant limitation of the Business Process Modeling Notation (BPMN): its weak data representation…
The focus of this paper is on reducing the complexity in verification by exploiting modularity at various levels: in specification, in verification, and structurally. For specifications, we use the modular language CSP-OZ-DC, which allows…
Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines supervise only the final response. To address this, we present…