A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Formalizes weak and strong verification for LLMs, controlling errors without assumptions.
Paper develops a model for verifying facts in tables without pre-retrieved evidence.
Paper develops PAC verification for hypothesis classes and statistical algorithms.
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…
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…
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the -norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large -norm perturbations,…
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…
Accelerating Speculative Diffusions via Block Verification
Researchers find floating point errors can mislead neural network verifiers.
Paper improves speaker verification with federated learning and differential privacy.
Robustness verification that aims to formally certify the prediction behavior of neural networks has become an important tool for understanding model behavior and obtaining safety guarantees. However, previous methods can usually only handle neural networks with relatively simple architectures. In this paper, we consid…
New methods combat data poisoning attacks in bandit algorithms using limited verification.
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 …
SFAVEL distills features from language models for fact verification without annotations.
New spoofing strategies show PoL verification is more vulnerable than previously thought.
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…
This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.
New models extrapolate false alarms in ASV without new data.
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 …
NTL protects AI models by restricting their generalization ability to specific domains.
Accelerates DNN robustness verification with target labels.
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…
This paper tackles robustness of ensemble stumps and trees under general ℓ_p norm perturbations.
Improves neural network verification by merging abstract domains and Lagrangian methods.
This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.
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) …
The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. In this context, verification involves proving or disproving that an NN model satisfies certain input-output properties. Despite the reputation of learned …
FUSE improves verification quality without ground truth labels.
Paper verifies RNNs using automata learning and model checking.
New method verifies formulas for causal interventional distributions.
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…
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.
Classification systems typically act in isolation, meaning they are required to implicitly memorize the characteristics of all candidate classes in order to classify. The cost of this is increased memory usage and poor sample efficiency. We propose a model which instead verifies using reference images during the classi…
Procedure verifies if machine learning models assign fixed predictions that preclude access.
Verification helps prevent model collapse when training on synthesized data.
Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variatio…
Formal verification of neural networks is essential for their deployment in safety-critical areas. Many available formal verification methods have been shown to be instances of a unified Branch and Bound (BaB) formulation. We propose a novel framework for designing an effective branching strategy for BaB. Specifically,…
Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in exponential time and relaxed verifiers that are efficient but incomplete. In this paper, we unify all existing LP-relaxed verifiers, to the best…
Extends branch and bound for probabilistic neural network verification.
In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that ar…
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
MaxRR efficiently unlearns models by splitting and selecting core samples.
New approach verifies tree ensembles efficiently, making them more robust.
GPUPoly verifies large neural networks robustly on GPUs.
NeuroDiff improves neural network equivalence verification with fine-grained approximations.
An empirical investigation of active/continuous authentication for smartphones is presented in this paper by exploiting users' unique application usage data, i.e., distinct patterns of use, modeled by a Markovian process. Variations of Hidden Markov Models (HMMs) are evaluated for continuous user verification, and chal…
FairCal improves face verification accuracy while making results fairer.