Related papers: ConstraintFlow: A DSL for Specification and Verifi…
Dynamic languages often employ reflection primitives to turn dynamically generated text into executable code at run-time. These features make standard static analysis extremely hard if not impossible because its essential data structures,…
We propose a novel way to incorporate expert knowledge into the training of deep neural networks. Many approaches encode domain constraints directly into the network architecture, requiring non-trivial or domain-specific engineering. In…
System relevant embedded software needs to be reliable and, therefore, well tested, especially for aerospace systems. A common technique to verify programs is the analysis of their abstract syntax tree (AST). Tree structures can be…
We propose denoising dictionary learning (DDL), a simple yet effective technique as a protection measure against adversarial perturbations. We examined denoising dictionary learning on MNIST and CIFAR10 perturbed under two different…
Neural networks in safety-critical applications face increasing safety and security concerns due to their susceptibility to little disturbance. In this paper, we propose DeepCDCL, a novel neural network verification framework based on the…
We focus on verifying relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations (UAP), certified worst-case hamming distance for binary string classifications, etc. Precise…
Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing…
Legal practitioners and judicial institutions face an ever-growing volume of case-law documents characterised by formalised language, lengthy sentence structures, and highly specialised terminology, making manual triage both time-consuming…
Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…
Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals. Provided the intractably large size of such input spaces, the…
Lighthouse projects such as CompCert, seL4, IronFleet, and DeepSpec have demonstrated that full verification of entire systems is feasible by establishing a refinement relation between an abstract system specification and an executable…
Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…
The quality of software products tends to correlate with the quality of the abstractions adopted early in the design process. Acknowledging this tendency has led to the development of various tools and methodologies for modeling systems…
The current work reports an efficient deep neural network (DNN) accelerator where synaptic weight elements are controlled by ferroelectric domain dynamics. An integrated device-to-algorithm framework for benchmarking novel synaptic devices…
Software Defined Networking (SDN) has been recently introduced as a new communication paradigm in computer networks. By separating the control plane from the data plane and entrusting packet forwarding to straightforward switches, SDN makes…
To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs…
We show that abstract interpretation-based static program analysis can be made efficient and precise enough to formally verify a class of properties for a family of large programs with few or no false alarms. This is achieved by refinement…
Inspired by the great success of recurrent neural networks (RNNs) in sequential modeling, we introduce a novel RNN system to improve the performance of online signature verification. The training objective is to directly minimize…
When creating a new domain-specific language (DSL) it is common to embed it as a part of a flexible host language, rather than creating it entirely from scratch. The semantics of an embedded DSL (EDSL) is either given directly as a set of…
Although Artificial Neural Networks (ANNs) have achieved remarkable success across various tasks, they still suffer from limited generalization. We hypothesize that this limitation arises from the traditional sample-based (0--dimensionnal)…