Research
On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

306191121 · May 202619922001200920172026
48 results for correctness verification

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

problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.

We present a novel framework for specifying and verifying correctness globally for neural networks on perception tasks. Most previous works on neural network verification for perception tasks focus on robustness verification. Unlike robustness verification, which aims to verify that the prediction of a network is stabl…

2019-06-03abs ↗pdf ↗

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…

2018-09-07abs ↗pdf ↗

A scalable protocol for federated averaging with privacy and correctness guarantees.

problem Privacy and correctness in federated learning from multiple parties.
method Scalable protocol using correlated and independent Gaussian noise, analyzed for differential privacy and graph topology.
result Nearly matches trusted curator model's utility with minimal communication.

Study loop corrections in random feature models affecting training and test errors.

problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the …

2018-05-06abs ↗pdf ↗

This research simplifies verification of machine learning systems using reparameterization.

problem Reduce or eliminate serious bugs in machine learning systems.
method Use proof assistants to construct machine-checked proofs of correctness, leveraging reparameterization to handle probabilistic claims.
result Demonstrates broad applicability of reparameterization to verify different types of machine learning systems.

Generalizes neural network verification by adding arbitrary cutting planes.

problem Handling general cutting plane constraints in neural network verification.
method Generalized bound propagation method (GCP-CROWN) that allows arbitrary cutting plane constraints.
result GCP-CROWN significantly improves neural network verification performance.

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

problem Balancing cost and reliability in reasoning with LLMs.
method Formalizes weak-strong verification policies, introduces metrics, develops online algorithm.
result Optimal policies admit a two-threshold structure, and calibration and sharpness govern value of weak verifiers.

Transformers learn to predict temporal logic solutions from classical solver outputs.

problem Training neural networks on logic problem solutions for verification.
method Training a Transformer on generated training data from classical solvers, focusing on one solution per formula.
result Transformers can predict correct solutions to temporal logic problems, even to unseen benchmarks.

Program verification offers a framework for ensuring program correctness and therefore systematically eliminating different classes of bugs. Inferring loop invariants is one of the main challenges behind automated verification of real-world programs which often contain many loops. In this paper, we present Continuous L…

2019-09-25abs ↗pdf ↗

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 …

2018-12-04abs ↗pdf ↗

Accelerates DNN robustness verification with target labels.

problem Improving the robustness of deep neural networks against adversarial attacks.
method Guiding robustness verification with target labels, reducing search space and using symbolic interval propagation and linear relaxation.
result Significantly improves DNN verification speed by 36X, especially when perturbation distance is reasonable.

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

problem Data poisoning attacks on bandit algorithms, especially in the UCB and ETC types.
method Verification-based mechanisms to restore optimal regret with limited verifications.
result A simple modified ETC type bandit algorithm can restore optimal regret with O(logT)O(\log T) verifications.

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…

2019-06-17abs ↗pdf ↗

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

problem Prove provable bounds for neural network outputs given input ranges.
method Uses zonotopes within a Lagrangian decomposition to verify deep neural networks.
result Yields bounds that improve upon existing techniques in both time and tightness.

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

problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.

This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service. A focus of Silas is on providing a formal foundation of decision trees in order to support logical analysis and verification of learned prediction models. This paper describes…

2019-10-03abs ↗pdf ↗

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

problem Verification of factual claims in structured data, especially in open-domain settings.
method Joint reranking-and-verification model that fuses evidence documents.
result Model achieves comparable performance to closed-domain state-of-the-art on TabFact dataset.

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…

2020-02-16abs ↗pdf ↗

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

problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.

Algorithm reconstructs triangle-free networks from data, certifying correctness.

problem Reconstructing triangle-free dynamic networks from observational data.
method Developed an algorithm for triangle-free networks, providing guarantees on correctness.
result Algorithm either certifies correctness or outputs a sparser graph with no false positives.

Researchers find floating point errors can mislead neural network verifiers.

problem Floating point arithmetic inaccuracies mislead neural network verifiers.
method Efficiently searches inputs and constructs neural network architectures to exploit verification errors.
result Floating point errors can systematically 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…

2019-06-10abs ↗pdf ↗

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

problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering LL_\infty-norm and pseudo-polynomial time for LpL_p-norm verification.
result Polynomial time verification for LL_\infty-norm attackers, NP-hard for other norms, and pseudo-polynomial time for LpL_p-norm verification.

The study develops a logic reasoner to verify MS case management specifications.

problem Ensuring correctness and solvability of abstract clinical work products.
method Developed a logic reasoner using UML class and state diagrams, SPIN, and ODM.
result Formal representations of UML diagrams proved consistent for MS case management.

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

problem The vulnerability of ensemble stumps and trees to small input perturbations under the ℓ_∞ norm.
method Developed dynamic programming algorithms for robustness verification and certified defense under general ℓ_p norm perturbations.
result First certified defense method for ensemble stumps and trees under ℓ_p norm perturbations.

New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative models of complex data. Experiments show that VAE provides speaker embedding and can be effectively trained in an unsupervised manner. LLR est…

2017-05-25abs ↗pdf ↗

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

problem Vulnerability of Proof-of-Learning verification mechanisms.
method Developed new spoofing strategies that can be reproduced across different configurations and are more cost-effective.
result Current PoL verification is not robust to adversaries and requires further understanding of optimization in deep learning.

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 …

2019-11-26abs ↗pdf ↗

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

problem Verifying the equivalence of compressed neural networks.
method Symbolic and fine-grained approximation technique for differential verification.
result NeuroDiff achieves up to 1000X speedup and 5X accuracy improvement.

Paper improves speaker verification with federated learning and differential privacy.

problem Improving speaker verification accuracy using private data.
method Combining federated learning and differential privacy to train an auxiliary model that predicts vocal characteristics.
result 6% relative improvement in equal error rate over a baseline system.