Search Results for author:
Found 20 papers, 12 papers with code
AIREPAIR: A Repair Platform for Neural Networks
We present AIREPAIR, a platform for repairing neural networks.
Safety Analysis of Autonomous Driving Systems Based on Model Learning
The safety properties proved in the resulting surrogate model apply to the original ADS with a probabilistic guarantee.
An Overview of Structural Coverage Metrics for Testing Neural Networks
Deep neural network (DNN) models, including those used in safety-critical domains, need to be thoroughly tested to ensure that they can reliably perform well in different scenarios.
VeriFi: Towards Verifiable Federated Unlearning
One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.
VPN: Verification of Poisoning in Neural Networks
Neural networks are successfully used in a variety of applications, many of them having safety and security concerns.
AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks
For correction, we propose an input correction technique that uses a differential analysis to identify the trigger in the detected poisoned images, which is then reset to a neutral color.
NNrepair: Constraint-based Repair of Neural Network Classifiers
We present novel strategies to enable precise yet efficient repair such as inferring correctness specifications to act as oracles for intermediate layer repair, and generation of experts for each class.
Explanations for Occluded Images
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded.
NEUROSPF: A tool for the Symbolic Analysis of Neural Networks
This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks.
RobOT: Robustness-Oriented Testing for Deep Learning Systems
A key part of RobOT is a quantitative measurement on 1) the value of each test case in improving model robustness (often via retraining), and 2) the convergence quality of the model robustness improvement.
Software Engineering
Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning
It is shown that DeepPAC outperforms the state-of-the-art statistical method PROVERO, and it achieves more practical robustness analysis than the formal verification tool ERAN.
Ranking Policy Decisions
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret.
Reliability Validation of Learning Enabled Vehicle Tracking
However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability.
Coverage Guided Testing for Recurrent Neural Networks
The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.
Explaining Image Classifiers using Statistical Fault Localization
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".
testRNN: Coverage-guided Testing on Recurrent Neural Networks
Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks.
Concolic Testing for Deep Neural Networks
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm
In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.
Testing Deep Neural Networks
In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics.
