2025
RvLLM: LLM Runtime Verification with Domain Knowledge.
CoRR, May, 2025

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems.
CoRR, April, 2025

Training Dynamics of In-Context Learning in Linear Attention.
CoRR, January, 2025

When Are Bias-Free ReLU Networks Effectively Linear Networks?
Trans. Mach. Learn. Res., 2025

Verification of Bit-Flip Attacks against Quantized Neural Networks.
Proc. ACM Program. Lang., 2025

SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers.
Proceedings of the 32nd Annual Network and Distributed System Security Symposium, 2025

2024
The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap.
CoRR, 2024

When Are Bias-Free ReLU Networks Like Linear Networks?
CoRR, 2024

A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion.
CoRR, 2024

SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems.
Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

Revisiting the Conflict-Resolving Problem from a Semantic Perspective.
Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering, 2024

Understanding Unimodal Bias in Multimodal Deep Linear Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Certified Quantization Strategy Synthesis for Neural Networks.
Proceedings of the Formal Methods - 26th International Symposium, 2024

Towards Efficient Verification of Quantized Neural Networks.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Compositional Verification of Efficient Masking Countermeasures against Side-Channel Attacks.
Proc. ACM Program. Lang., October, 2023

Precise Quantitative Analysis of Binarized Neural Networks: A BDD-based Approach.
ACM Trans. Softw. Eng. Methodol., May, 2023

A Theory of Unimodal Bias in Multimodal Learning.
CoRR, 2023

QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems.
Proceedings of the 32nd USENIX Security Symposium, 2023

QEBVerif: Quantization Error Bound Verification of Neural Networks.
Proceedings of the Computer Aided Verification - 35th International Conference, 2023

2022
QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks.
CoRR, 2022

CLEVEREST: Accelerating CEGAR-based Neural Network Verification via Adversarial Attacks.
Proceedings of the Static Analysis - 29th International Symposium, 2022

QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks.
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, 2022

2021
BDD4BNN: A BDD-Based Quantitative Analysis Framework for Binarized Neural Networks.
Proceedings of the Computer Aided Verification - 33rd International Conference, 2021

2019
Making Agents' Abilities Explicit.
IEEE Access, 2019

Probabilistic Alternating-Time <i>µ</i>-Calculus.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019