arXiv research

Paper develops a model for verifying facts in tables without pre-retrieved evidence.

Study consumption-investment problem in markets with rank-based returns.

A method for rank verification in multivariate Gaussian data, improving on existing approaches.

Verifying probabilistic forecasts for extreme events is a highly active research area because popular media and public opinions are naturally focused on extreme events, and biased conclusions are readily made. In this context, classical verification methods tailored for extreme events, such as thresholded and weighted …

A Riemannian manifold is said to be almost positively curved if the sets of points for which all $2$-planes have positive sectional curvature is open and dense. We show that the Grassmannian of oriented $2$-planes in $\mathbb{R}^7$ admits a metric of almost positive curvature, giving the first example of an almost posi…

Formalizes weak and strong verification for LLMs, controlling errors without assumptions.

EORM boosts LLM accuracy with a lightweight, energy-based verifier.

The report analyzes Legendre decomposition for tensor data.

Develops first robustness verification for complex Transformers.

Paper develops PAC verification for hypothesis classes and statistical algorithms.

Hypothesis testing is an important problem with applications in target localization, clinical trials etc. Many active hypothesis testing strategies operate in two phases: an exploration phase and a verification phase. In the exploration phase, selection of experiments is such that a moderate level of confidence on the …

We explore the concept of co-design in the context of neural network verification. Specifically, we aim to train deep neural networks that not only are robust to adversarial perturbations but also whose robustness can be verified more easily. To this end, we identify two properties of network models - weight sparsity a…

Accelerates DNN robustness verification with target labels.

New methods combat data poisoning attacks in bandit algorithms using limited verification.

In this paper we demonstrate that performance of a speaker verification system can be improved by concatenating electroencephalography (EEG) signal features with speech signal features or only using EEG signal features. We use state-of-the-art end-to-end deep learning model for performing speaker verification and we de…

Improves neural network verification by merging abstract domains and Lagrangian methods.

This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.

Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.

Researchers find floating point errors can mislead neural network verifiers.

We study the robustness verification problem for tree-based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness verification of decision tree ensembles involves finding the exact minimal adversarial perturbation or a guaranteed lower bound of it. Existin…

This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.

Accelerating Speculative Diffusions via Block Verification

Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the $\ell_p$-norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large $\ell_p$-norm perturbations,…

This paper tackles robustness of ensemble stumps and trees under general ℓ_p norm perturbations.

The ASVspoof challenge series was born to spearhead research in anti-spoofing for automatic speaker verification (ASV). The two challenge editions in 2015 and 2017 involved the assessment of spoofing countermeasures (CMs) in isolation from ASV using an equal error rate (EER) metric. While a strategic approach to assess…

GPUPoly verifies large neural networks robustly on GPUs.

New spoofing strategies show PoL verification is more vulnerable than previously thought.

We present a scoring approach for speaker verification that mimics the standard PLDA-based backend process used in most current speaker verification systems. However, unlike the standard backends, all parameters of the model are jointly trained to optimize the binary cross-entropy for the speaker verification task. We …

NeuroDiff improves neural network equivalence verification with fine-grained approximations.

HabitatAgent offers a multi-agent system for transparent housing consultation.

FPGAs have become a popular choice for deploying deep learning architectures (DLA). There are many researchers that have explored the deployment and mapping of DLA on FPGA. However, there has been a growing need to do design-time hardware-software co-verification of these deployments. To the best of our knowledge this …

Novel approach using Lagrangian Decomposition for neural network verification.

Validates neural networks inputs to protect against adversarial examples.

Paper improves speaker verification with federated learning and differential privacy.

This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output an embedding vector which distinguishes the speaker characteristics of the input utterance, while th…

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that neural networks satisfy specifications relating their inputs and outputs (robustness to bounded norm adversarial perturbations, for example). Most previous work on this topic was limi…

SFAVEL distills features from language models for fact verification without annotations.

Scalable verification for deep neural networks with formal guarantees.

Improved far-field speaker verification for short utterances in noisy conditions.

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with similar approaches, we do not extract the embedding of an utterance from the mean redu…

Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not. A range of successful technical approaches has been proposed for this task, many of which are based on traditional linguistic features such as n-grams. These algorithms achieve good results…

An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification based on the SVMs classifier, in text independent mode. This approach combines features based on conven…

The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish g…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …

In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs). The networks perform feature mapping between the spectral features of reverberant and clean speech. Long short term memory recurrent neural networks (LSTMs) are trained to map corrupted…

New method improves neural network verification by considering multivariate input space of ReLU neurons.

Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. W…

We propose a framework for verifying data deletion in MLaaS systems.