arXiv:2602.05068v1 Announce Type: new Abstract: Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness trade-off. We propose a hybrid verifier in a branch-and-bound (BaB) framework that efficiently tightens both upper and lower bounds until an $epsilon-$global optimum is reached or early stop is triggered. The key is an exact nonlinear program with complementarity constraints (NLP-CC) for upper bounding that preserves the […]

Ver mais

arXiv:2603.10060v1 Announce Type: new Abstract: AI agents that execute tasks via tool calls frequently hallucinate results – fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge proofs, which provide cryptographic guarantees but impose minutes of proving time per query, making them impractical for interactive agents. We propose NabaOS, a lightweight verification framework inspired by Indian epistemology (Nyaya Shastra), which classifies every claim in an LLM response by […]

Ver mais

arXiv:2603.01157v1 Announce Type: cross Abstract: Risk forecasts in financial regulation and internal management are calculated through historical data. The unknown structural changes of financial data poses a substantial challenge in selecting an appropriate look-back window for risk modeling and forecasting. We develop a data-driven online learning method, called the bootstrap-based adaptive window selection (BAWS), that adaptively determines the window size in a sequential manner. A central component of BAWS is to compare the realized scores against a data-dependent […]

Ver mais

arXiv:2602.04927v1 Announce Type: new Abstract: Artificial intelligence systems introduce complex privacy risks throughout their lifecycle, especially when processing sensitive or high-dimensional data. Beyond the seven traditional privacy threat categories defined by the LINDDUN framework, AI systems are also exposed to model-centric privacy attacks such as membership inference and model inversion, which LINDDUN does not cover. To address both classical LINDDUN threats and additional AI-driven privacy attacks, PriMod4AI introduces a hybrid privacy threat modeling approach that unifies two structured […]

Ver mais

arXiv:2602.03394v1 Announce Type: new Abstract: Deep neural networks (DNNs) often produce overconfident out-of-distribution predictions, motivating Bayesian uncertainty quantification. The Linearized Laplace Approximation (LLA) achieves this by linearizing the DNN and applying Laplace inference to the resulting model. Importantly, the linear model is also used for prediction. We argue this linearization in the posterior may degrade fidelity to the true Laplace approximation. To alleviate this problem, without increasing significantly the computational cost, we propose the Quadratic Laplace Approximation (QLA). […]

Ver mais

arXiv:2602.13274v1 Announce Type: new Abstract: Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark evaluating 11 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our new robustness test, ETHICS-Contrast, we measure performance via our proposed Unified Moral Safety Score (UMSS), a metric balancing accuracy and safety. Our results show that compact, exemplar-guided scaffolds outperform complex […]

Ver mais

arXiv:2603.22335v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and theoretical analysis reveal that DPO tends to amplify spurious correlations caused by environmental confounders during the alignment process, significantly undermining the generalization capability of LLM-based generative recommendation methods in out of distribution (OOD) scenarios. To mitigate this issue, we propose CausalDPO, an extension of […]

Ver mais

arXiv:2601.05404v1 Announce Type: new Abstract: Optimal damping aims at determining a vector of damping coefficients $nu$ that maximizes the decay rate of a mechanical system’s response. This problem can be formulated as the minimization of the trace of the solution of a Lyapunov equation whose coefficient matrix depends on $nu$. For physical relevance, the damping coefficients must be nonnegative and the resulting system must be asymptotically stable. We identify conditions under which the system is never stable or […]

Ver mais