Dr. rer. nat.

Cheng, Chih-Hong

Filters

3 1
Reset filters

Settings
Now showing 1 - 4 of 4
  • Publication
    Safety Performance of Neural Networks in the Presence of Covariate Shift
    ( 2024)
    Cheng, Chih-Hong
    ;
    Ruess, Harald
    ;
    Theodorou, Konstantinos
    Covariate shift may impact the operational safety performance of neural networks. A re-evaluation of the safety performance, however, requires collecting new operational data and creating corresponding ground truth labels, which often is not possible during operation. We are therefore proposing to reshape the initial test set, as used for the safety performance evaluation prior to deployment, based on an approximation of the operational data. This approximation is obtained by observing and learning the distribution of activation patterns of neurons in the network during operation. The reshaped test set reflects the distribution of neuron activation values as observed during operation, and may therefore be used for re-evaluating safety performance in the presence of covariate shift. First, we derive conservative bounds on the values of neurons by applying finite binning and static dataflow analysis. Second, we formulate a mixed integer linear programming (MILP) constraint for constructing the minimum set of data points to be removed in the test set, such that the difference between the discretized test and operational distributions is bounded. We discuss potential benefits and limitations of this constraint-based approach based on our initial experience with an implemented research prototype.
  • Publication
    Potential-based Credit Assignment for Cooperative RL-based Testing of Autonomous Vehicles
    ( 2023)
    Ayvaz, Utku
    ;
    Cheng, Chih-Hong
    ;
    Hao, Shen
    While autonomous vehicles (AVs) may perform remarkably well in generic real-life cases, their irrational action in some unforeseen cases leads to critical safety concerns. This paper introduces the concept of collaborative reinforcement learning (RL) to generate challenging test cases for AV planning and decision-making module. One of the critical challenges for collaborative RL is the credit assignment problem, where a proper assignment of rewards to multiple agents interacting in the traffic scenario, considering all parameters and timing, turns out to be non-trivial. In order to address this challenge, we propose a novel potential-based reward-shaping approach inspired by counterfactual analysis for solving the credit-assignment problem. The evaluation in a simulated environment demonstrates the superiority of our proposed approach against other methods using local and global rewards.
  • Publication
    Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
    ( 2023)
    Liao, Brian Hsuan-Cheng
    ;
    Cheng, Chih-Hong
    ;
    Esen, Hasan
    ;
    Knoll, Alois
    As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving. In this paper, we study the robustness problem of Transformers, a key characteristic as low robustness may cause safety concerns. Specifically, we focus on Sparsemax-based Transformers and reduce the finding of their maximum robustness to a Mixed Integer Quadratically Constrained Programming (MIQCP) problem. We also design two pre-processing heuristics that can be embedded in the MIQCP encoding and substantially accelerate its solving. We then conduct experiments using the application of Land Departure Warning to compare the robustness of Sparsemax-based Transformers against that of the more conventional Multi-Layer-Perceptron (MLP) NNs. To our surprise, Transformers are not necessarily more robust, leading to profound considerations in selecting appropriate NN architectures for safety-critical domain applications.
  • Publication
    Formal Specification for Learning-Enabled Autonomous Systems
    ( 2022)
    Bensalem, Saddek
    ;
    Cheng, Chih-Hong
    ;
    Huang, Xiaowei
    ;
    Katsaros, Panagiotis
    ;
    Molin, Adam
    ;
    Nickovic, Dejan
    ;
    Peled, Doron
    The formal specification provides a uniquely readable description of various aspects of a system, including its temporal behavior. This facilitates testing and sometimes automatic verification of the system against the given specification. We present a logic-based formalism for specifying learning-enabled autonomous systems, which involve components based on neural networks. The formalism is based on first-order past time temporal logic that uses predicates for denoting events. We have applied the formalism successfully to two complex use cases.