Search Results for author:
Found 13 papers, 4 papers with code
ADVREPAIR:Provable Repair of Adversarial Attack
Existing neuron-level methods using limited data lack efficacy in fixing adversaries due to the inherent complexity of adversarial attack mechanisms, while adversarial training, leveraging a large number of adversarial samples to enhance robustness, lacks provability.
DeepCDCL: An CDCL-based Neural Network Verification Framework
Neural networks in safety-critical applications face increasing safety and security concerns due to their susceptibility to little disturbance.
TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
Firstly, the previous definitions of robustness in trajectory prediction are ambiguous.
Incremental Satisfiability Modulo Theory for Verification of Deep Neural Networks
Moreover, based on the framework, we propose the multi-objective DNN repair problem and give an algorithm based on our incremental SMT solving algorithm.
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.
Microservice Deployment in Edge Computing Based on Deep Q Learning
Then, we propose a multi-objective microservice deployment problem (MMDP) in edge computing.
Weight Expansion: A New Perspective on Dropout and Generalization
While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking.
Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness
In this paper, we propose a framework of filter-based ensemble of deep neuralnetworks (DNNs) to defend against adversarial attacks.
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.
Improving Neural Network Verification through Spurious Region Guided Refinement
The core idea is to make use of the obtained constraints of the abstraction to infer new bounds for the neurons.
Asymptotically Optimal One- and Two-Sample Testing with Kernels
With Sanov's theorem, we derive a sufficient condition for one-sample tests to achieve the optimal error exponent in the universal setting, i. e., for any distribution defining the alternative hypothesis.
Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification
Several verification approaches have been developed to automatically prove or disprove safety properties of DNNs.
Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit
We show that two classes of Maximum Mean Discrepancy (MMD) based tests attain this optimality on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve the maximum exponential decay rate under a relaxed level constraint.
