SFAVEL distills features from language models for fact verification without annotations.
problem Fact verification with semantically meaningful and compact features.
method Self-supervised pretraining using contrastive loss with language models.
result Achieved state-of-the-art results on FB15k-237 and FEVER.
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.
We create a large dataset for fact checking claims and improve prediction accuracy.
problem Fact checking claims from multiple sources is challenging.
method We created a comprehensive dataset and developed a novel method for automatic veracity prediction.
result Our model achieves a Macro F1 of 49.2%, showing significant performance improvements.
Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of evidence for verification. However, previous work employs simple models to extract info…
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.
The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. The objective of signature verification systems is to discriminate if a given signature is genuine (produced by the claimed individual), or a forgery (produced by an impostor). This has …
Unified framework certifies predictor performance under distribution shift.
problem Certifying predictor performance under distribution shift.
method Unified framework with explicit inequalities, sound verification, and identifiable structure.
result Explicit upper bound on excess risk under shift.
Study optimal reinsurance and investment strategies under common shocks affecting financial and actuarial markets.
problem Maximizing expected exponential utility of terminal wealth in a company facing both ordinary and catastrophic claims.
method Modeling common shocks affecting financial and actuarial markets, using stochastic control and Hamilton-Jacobi-Bellman equations.
result Characterization of optimal reinsurance and investment strategies under common shock dependence.
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.
CausalForge automates causal inference research with formal proofs and self-improvement.
problem Unreliable evaluation of automated research results by large language models.
method Formal proof assistant (Lean) and self-improving agentic pipeline.
result Automated research produces reliable formal proofs and artifacts.
We study the optimal excess-of-loss reinsurance problem when both the intensity of the claims arrival process and the claim size distribution are influenced by an exogenous stochastic factor. We assume that the insurer's surplus is governed by a marked point process with dual-predictable projection affected by an envir…
PEREGRiNN verifies safety of ReLU NNs by penalizing relaxation in a greedy manner.
problem Formal verification of safety specifications for ReLU NNs.
method Uses a relaxed convex program to verify polytopic input/output constraints, penalizing relaxation and forcing largest relaxations to early layers.
result Significantly faster and more properties verified compared to other approaches.
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.
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is trainable with gradient-based methods yet achieves near-optimal performance via submodular optimization. We focus on the task of identifying …
New algorithms verify and search causal graphs with minimal interventions.
problem Recovering causal graphs from interventional data.
method Characterization of minimal intervention sets for verification, and adaptive graph separator algorithm for search.
result First provable algorithms for efficient verification and search of causal graphs.
PRoA assesses deep learning robustness against practical functional perturbations.
problem Inadequate practical robustness verification methods for deep learning systems.
method Probabilistic robustness assessment based on adaptive concentration.
result Statistical guarantees on probabilistic robustness against functional perturbations.
Develops first robustness verification for complex Transformers.
problem Certify prediction behavior of Transformers with complex self-attention layers.
method Resolves challenges of cross-nonlinearity and cross-position dependency in Transformers.
result Certified robustness bounds are significantly tighter than Interval Bound Propagation.
New method generates optical vortices in any knot shape.
problem Generating optical vortices in complex shapes beyond simple knots.
method Mathematical construction and experimental verification.
result Complex optical fields can form any knot shape.
Paper develops PAC verification for hypothesis classes and statistical algorithms.
problem Verifying machine learning models interactively.
method Develops interactive proof for PAC verification, proves lower bounds, and introduces a generalization.
result Improved protocol for verifying unions of intervals and statistical query algorithms.
Language models perform worse with implicit reward models than explicit ones.
problem Understanding why implicit reward models generalize worse than explicit ones.
method Investigated the root cause of the generalization gap between IM-RMs and EX-RMs.
result Implicit reward models rely more on superficial token-level cues, leading to worse generalization.
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…
Develops a framework to analyze financial structures.
problem Difficulty in systematic analysis, comparison, and verification of financial structures.
method Formalizes financial structures as structured allocation systems with explicit allocation operators.
result Specifies inputs, structural requirements, and feasibility restrictions for financial structures.
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) verifications. Improved speaker verification with condition-aware backend.
problem Speaker verification calibration issues under unknown conditions.
method Discriminative PLDA model with joint training and condition integration.
result Out-of-the-box excellent calibration performance.
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.
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.
System detects financial misinformation and generates clear explanations.
problem Identifying and explaining fraudulent financial content.
method Combined large language models, pre-processing, and sequential learning.
result Achieved F1-score of 0.8283 for classification and ROUGE-1 of 0.7253 for explanations.
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.
In this work we investigate the optimal proportional reinsurance-investment strategy of an insurance company which wishes to maximize the expected exponential utility of its terminal wealth in a finite time horizon. Our goal is to extend the classical Cramer-Lundberg model introducing a stochastic factor which affects …
We study a continuous-time asset-allocation problem for an insurance firm that backs up liabilities from multiple non-life business lines with underwriting profits and investment income. The insurance risks are captured via a multidimensional jump-diffusion process with a multivariate compound Poisson process with depe…
Study finds no significant alignment between whitepaper claims and market structure.
problem Correlation between cryptocurrency whitepaper narratives and market behavior.
method Developed a contamination-aware pipeline for measuring structural correspondence, combining NLP classification and market statistics.
result No significant claims-market alignment detected in the sample.
Paper shows incorrectness of approximate unlearning definitions and challenges exact unlearning verification.
problem Incorrectness of approximate unlearning definitions and challenges in verifying exact unlearning.
method Analysis of machine unlearning approaches, including exact and approximate methods.
result Unlearning is only well-defined at the algorithmic level, and auditable claims are limited.
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.
Semantify-NN verifies neural network robustness against semantic perturbations.
problem Verifying robustness of neural networks against semantic adversarial attacks.
method Inserting semantic perturbation layers (SP-layers) into neural networks to verify robustness.
result Semantify-NN significantly improves robustness verification performance over ℓp-norm-based methods. 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.
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 L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. Accelerating Speculative Diffusions via Block Verification
problem Adapting speculative decoding for continuous diffusion models
method Introducing a novel speculative sampling mechanism for diffusion models
result Improves acceptance rate and speeds up inference
We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation. These statistics are useful for approximate whitening of the inputs in front of saturating non-linearities such as a sigmoid function. This is important for initialization of training and f…
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.
A new method for verifying deep learning architectures on FPGAs is proposed.
problem Design-time verification of deep learning architectures on FPGAs.
method 2-Level 3-Way (2L-3W) hardware-software co-verification methodology.
result Layer-by-layer similarity scores of 99% accuracy for successful mappings.
New algorithms improve neural network verification by exploiting piecewise linear structure.
problem Efficiently verify the correctness of neural networks, especially those with high-dimensional inputs.
method Branch-and-Bound (BaB) framework applied to Mixed Integer Linear Programming (MIP) formulation.
result Significant performance improvements and new branching strategies for neural networks.
A neural network learns to improve verification of neural networks.
problem Efficient verification of neural networks for safety-critical applications.
method A graph neural network (GNN) learns to imitate strong branching heuristics for effective branching in the Branch and Bound (BaB) formulation.
result Reduces the number of branches and verification time by roughly 50% compared to hand-designed strategies.
Paper proposes a new method for robust speaker verification.
problem Improving robustness in speaker verification systems.
method Combines soft VAD and self-adaptive VAD with DNN-based VAD.
result Significant improvement in verification performance in real-world environments.
GPUPoly verifies large neural networks robustly on GPUs.
problem Proving robustness of deep neural networks is crucial but challenging.
method Custom polyhedra algorithms on GPUs.
result GPUPoly can verify 1M neuron networks in 34.5 ms.
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.
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.