arXiv subjects

Vahid Hashemi

Publications and source records attributed to Vahid Hashemi.

16 recordsLinked to original sources

arXiv2026

Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting

Time series forecasting is a fundamental machine learning task. Recent work has explored Large Language Models (LLMs) for this purpose due to their strong generalization, pattern recognition, and zero-shot or few-shot capabilities. Despite their suitability for long-context learning, LLMs face challenges in multimodal settings: they lack calibrated probabilistic modeling for non-text data and struggle to align heterogeneous representations. To address these issues, we propose a new framework Diffusion-LLM that integrates a conditional diffusion model into an LLM-based forecasting pipeline. This joint design enables learning the conditional distribution of future data while improving semantic alignment in a shared latent space. We evaluate Diffusion-LLM on six long-term forecasting benchmarks, including ETT, Weather, and ECL. Our method consistently outperforms existing LLM-based baseline, achieving notable gains in ultra-long-term and few-shot forecasting and demonstrating the value of distribution-aware regularization for enhancing robustness and generalization in time series LLMs.

cs.LG↗

arXiv2024

Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directions

Automated vehicles (AVs) promise to enhance transportation safety and efficiency. However, ensuring their reliability in real-world conditions remains challenging, particularly due to rare and unexpected situations known as edge cases. While numerous approaches exist for detecting edge cases, a comprehensive survey reviewing these techniques is lacking. This paper bridges this gap by presenting a hierarchical review and systematic classification of edge case detection and assessment methodologies. Our classification is structured on two levels: first, by AV modules, including perception and trajectory-related (encompassing prediction, planning, and control) subsystems; and second, by underlying methodologies and theories guiding these techniques. Furthermore, we introduce "knowledge-driven" approaches, which complement data-driven methods by leveraging expert insights and domain knowledge to identify cases absent in training datasets. We then examine techniques and metrics for evaluating edge case detection methods, including detection performance, practical deployment (e.g., computational overhead), and domain-specific measures (e.g., crash rates and severity analysis). We conclude by highlighting key challenges for edge case detection, including data availability and quality issues, validation and interpretability limitations, the simulation-to-real gap, and computational constraints. The hierarchical classification and review of methods and assessment techniques in this survey enable modular and targeted testing frameworks by guiding the selection of detection methods for specific AV subsystems while considering methodological principles. It also supports practical testing by facilitating scenario generation in simulation and focused subsystem validation in the real world.

cs.RO↗

arXiv2024

Autonomous Vehicles Path Planning under Temporal Logic Specifications

Path planning is an essential component of autonomous driving. A global planner is responsible for the high-level planning. It basically performs a shortest-path search on a known map, thereby defining waypoints used to control the local (low-level) planner. Local planning is a runtime verification method which is repeatedly run on the vehicle itself in real-time, so as to find the optimal short-horizon path which leads to the desired waypoint in a way which is both efficient and safe. The challenge is that the local planner has to take into account repeatedly incoming updates about the information available of the environment. In addition, it performs a complex task, as it has to take into account a large variety of requirements, originating from the necessity of collision avoidance with obstacles, respecting traffic rules, sticking to regulatory requirements, and lastly to reach the next waypoint efficiently. In this paper, we describe a logic-based specification mechanism which fulfills all these requirements.

cs.RO↗

arXiv2024

Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces

Since neural networks can make wrong predictions even with high confidence, monitoring their behavior at runtime is important, especially in safety-critical domains like autonomous driving. In this paper, we combine ideas from previous monitoring approaches based on observing the activation values of hidden neurons. In particular, we combine the Gaussian-based approach, which observes whether the current value of each monitored neuron is similar to typical values observed during training, and the Outside-the-Box monitor, which creates clusters of the acceptable activation values, and, thus, considers the correlations of the neurons' values. Our experiments evaluate the achieved improvement.

cs.LG↗

arXiv2023

AGNES: Abstraction-guided Framework for Deep Neural Networks Security

Deep Neural Networks (DNNs) are becoming widespread, particularly in safety-critical areas. One prominent application is image recognition in autonomous driving, where the correct classification of objects, such as traffic signs, is essential for safe driving. Unfortunately, DNNs are prone to backdoors, meaning that they concentrate on attributes of the image that should be irrelevant for their correct classification. Backdoors are integrated into a DNN during training, either with malicious intent (such as a manipulated training process, because of which a yellow sticker always leads to a traffic sign being recognised as a stop sign) or unintentional (such as a rural background leading to any traffic sign being recognised as animal crossing, because of biased training data). In this paper, we introduce AGNES, a tool to detect backdoors in DNNs for image recognition. We discuss the principle approach on which AGNES is based. Afterwards, we show that our tool performs better than many state-of-the-art methods for multiple relevant case studies.

cs.LG↗

arXiv2023

Causal Analysis for Robust Interpretability of Neural Networks

Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to individual examples. However, these measures are susceptible to noise and spurious correlations encoded in the model during the training phase (e.g., biased inputs, model overfitting, or misspecification). Moreover, this process has proven to result in noisy and unstable attributions that prevent any transparent understanding of the model's behavior. In this paper, we develop a robust interventional-based method grounded by causal analysis to capture cause-effect mechanisms in pre-trained neural networks and their relation to the prediction. Our novel approach relies on path interventions to infer the causal mechanisms within hidden layers and isolate relevant and necessary information (to model prediction), avoiding noisy ones. The result is task-specific causal explanatory graphs that can audit model behavior and express the actual causes underlying its performance. We apply our method to vision models trained on classification tasks. On image classification tasks, we provide extensive quantitative experiments to show that our approach can capture more stable and faithful explanations than standard attribution-based methods. Furthermore, the underlying causal graphs reveal the neural interactions in the model, making it a valuable tool in other applications (e.g., model repair).

cs.LG↗

arXiv2022

Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks

Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.

cs.LG↗

arXiv2022

Backdoor Mitigation in Deep Neural Networks via Strategic Retraining

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed reasonably using traditional software development methods. DNN however do have the problem that they are mostly black boxes and therefore hard to understand and debug. One particular problem is that they are prone to hidden backdoors. This means that the DNN misclassifies its input, because it considers properties that should not be decisive for the output. Backdoors may either be introduced by malicious attackers or by inappropriate training. In any case, detecting and removing them is important in the automotive area, as they might lead to safety violations with potentially severe consequences. In this paper, we introduce a novel method to remove backdoors. Our method works for both intentional as well as unintentional backdoors. We also do not require prior knowledge about the shape or distribution of backdoors. Experimental evidence shows that our method performs well on several medium-sized examples.

cs.CR↗

arXiv2022

SMC4PEP: Stochastic Model Checking of Product Engineering Processes

Product Engineering Processes (PEPs) are used for describing complex product developments in big enterprises such as automotive and avionics industries. The Business Process Model Notation (BPMN) is a widely used language to encode interactions among several participants in such PEPs. In this paper, we present SMC4PEP as a tool to convert graphical representations of a business process using the BPMN standard to an equivalent discrete-time stochastic control process called Markov Decision Process (MDP). To this aim, we first follow the approach described in an earlier investigation to generate a semantically equivalent business process which is more capable of handling the PEP complexity. In particular, the interaction between different levels of abstraction is realized by events rather than direct message flows. Afterwards, SMC4PEP converts the generated process to an MDP model described by the syntax of the probabilistic model checking tool PRISM. As such, SMC4PEP provides a framework for automatic verification and validation of business processes in particular with respect to requirements from legal standards such as Automotive SPICE. Moreover, our experimental results confirm a faster verification routine due to smaller MDP models generated from the alternative event-based BPMN models.

cs.LO↗

arXiv2020

Towards a Systems Engineering based Automotive Product Engineering Process

Deficit and redundancies in existing automotive product development hinder a systems engineering based development. In this paper we discuss a methodical procedure to eliminate deficits in the current product development and in turn to enable the introduction of a new systems engineering based development methodology. As the core part of our approach, we discuss how to transform an opaque heterogeneous product development to a homogenous consistent product development taking into account existing disciplines. Our approach paves the way to achieve a process structure that is more amenable to verification and validation. We show the effectiveness of our proposed solution approach on an automotive use case.

cs.SE↗

arXiv2020

DeepAbstract: Neural Network Abstraction for Accelerating Verification

While abstraction is a classic tool of verification to scale it up, it is not used very often for verifying neural networks. However, it can help with the still open task of scaling existing algorithms to state-of-the-art network architectures. We introduce an abstraction framework applicable to fully-connected feed-forward neural networks based on clustering of neurons that behave similarly on some inputs. For the particular case of ReLU, we additionally provide error bounds incurred by the abstraction. We show how the abstraction reduces the size of the network, while preserving its accuracy, and how verification results on the abstract network can be transferred back to the original network.

cs.LO↗

arXiv2019

Towards Safety Verification of Direct Perception Neural Networks

We study the problem of safety verification of direct perception neural networks, where camera images are used as inputs to produce high-level features for autonomous vehicles to make control decisions. Formal verification of direct perception neural networks is extremely challenging, as it is difficult to formulate the specification that requires characterizing input as constraints, while the number of neurons in such a network can reach millions. We approach the specification problem by learning an input property characterizer which carefully extends a direct perception neural network at close-to-output layers, and address the scalability problem by a novel assume-guarantee based verification approach. The presented workflow is used to understand a direct perception neural network (developed by Audi) which computes the next waypoint and orientation for autonomous vehicles to follow.

cs.SE↗

arXiv2017

Multi-Objective Approaches to Markov Decision Processes with Uncertain Transition Parameters

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not known precisely. Different types of MDPs with uncertain, imprecise or bounded transition rates or probabilities and rewards exist in the literature. Commonly, analysis of models with uncertainties amounts to searching for the most robust policy which means that the goal is to generate a policy with the greatest lower bound on performance (or, symmetrically, the lowest upper bound on costs). However, hedging against an unlikely worst case may lead to losses in other situations. In general, one is interested in policies that behave well in all situations which results in a multi-objective view on decision making. In this paper, we consider policies for the expected discounted reward measure of MDPs with uncertain parameters. In particular, the approach is defined for bounded-parameter MDPs (BMDPs) [8]. In this setting the worst, best and average case performances of a policy are analyzed simultaneously, which yields a multi-scenario multi-objective optimization problem. The paper presents and evaluates approaches to compute the pure Pareto optimal policies in the value vector space.

cs.AI↗

arXiv2017

Multi-objective Robust Strategy Synthesis for Interval Markov Decision Processes

Interval Markov decision processes (IMDPs) generalise classical MDPs by having interval-valued transition probabilities. They provide a powerful modelling tool for probabilistic systems with an additional variation or uncertainty that prevents the knowledge of the exact transition probabilities. In this paper, we consider the problem of multi-objective robust strategy synthesis for interval MDPs, where the aim is to find a robust strategy that guarantees the satisfaction of multiple properties at the same time in face of the transition probability uncertainty. We first show that this problem is PSPACE-hard. Then, we provide a value iteration-based decision algorithm to approximate the Pareto set of achievable points. We finally demonstrate the practical effectiveness of our proposed approaches by applying them on several case studies using a prototypical tool.

eess.SY↗

arXiv2016

Compositional Reasoning for Interval Markov Decision Processes

Model checking probabilistic CTL properties of Markov decision processes with convex uncertainties has been recently investigated by Puggelli et al. Such model checking algorithms typically suffer from the state space explosion. In this paper, we address probabilistic bisimulation to reduce the size of such an MDP while preserving the probabilistic CTL properties it satisfies. In particular, we discuss the key ingredients to build up the operations of parallel composition for composing interval MDP components at run-time. More precisely, we investigate how the parallel composition operator for interval MDPs can be defined so as to arrive at a congruence closure. As a result, we show that probabilistic bisimulation for interval MDPs is congruence with respect to two facets of parallelism, namely synchronous product and interleaving.

cs.LO↗

arXiv2014

Probabilistic Bisimulations for PCTL Model Checking of Interval MDPs

Verification of PCTL properties of MDPs with convex uncertainties has been investigated recently by Puggelli et al. However, model checking algorithms typically suffer from state space explosion. In this paper, we address probabilistic bisimulation to reduce the size of such an MDPs while preserving PCTL properties it satisfies. We discuss different interpretations of uncertainty in the models which are studied in the literature and that result in two different definitions of bisimulations. We give algorithms to compute the quotients of these bisimulations in time polynomial in the size of the model and exponential in the uncertain branching. Finally, we show by a case study that large models in practice can have small branching and that a substantial state space reduction can be achieved by our approach.

cs.FL↗