4 citations · 6 across the 4 of their papers we have counts for
8 papers
Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations
Hai Duong, Thanh Le, Ho Nguyen +1
Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically affect multiple parameters…
CLAD: Constrained Abstract Domain for Neural Network Verification
Hai Duong, Thanh Le, ThanhVu Nguyen
Neural network verification (NNV) formally verifies that a network satisfies a specified property for all inputs within a defined region. Modern NNV tools employ abstract domains t…
Verifying Neural Networks with Reinforcement Learning
Hai Duong, Thanh Le, ThanhVu Nguyen
Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems. Modern DNN verifiers employ a branch-and-bou…
ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models
Hai Duong, Thanh Le, ThanhVu Nguyen
Transformer-based models are widely used for reasoning, coding, and multimodal agentic tasks. To provide formal assurance of desirable behaviors, such as robustness, safety, and fa…
Verifying DNN-based Semantic Communication Against Generative Adversarial Noise
Thanh Le, Hai Duong, ThanhVu Nguyen +1
Safety-critical applications like autonomous vehicles and industrial IoT are adopting semantic communication (SemCom) systems using deep neural networks to reduce bandwidth and inc…
The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results
Konstantin Kaulen, Tobias Ladner, Stanley Bak +8
This report summarizes the 6th International Verification of Neural Networks Competition (VNN-COMP 2025), held as a part of the 8th International Symposium on AI Verification (SAIV…
FGGM: Formal Grey-box Gradient Method for Attacking DRL-based MU-MIMO Scheduler
Thanh Le, Hai Duong, Yusheng Ji +2
In 5G mobile communication systems, MU-MIMO has been applied to enhance spectral efficiency and support high data rates. To maximize spectral efficiency while providing fairness am…
Harnessing Neuron Stability to Improve DNN Verification
Hai Duong, Dong Xu, ThanhVu Nguyen +1
Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. Th…