43 citations · 61 across the 22 of their papers we have counts for
6 papers · 1 filter
Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models
Nay Myat Min, Long H. Pham, Jun Sun
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subver…
CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
Nay Myat Min, Long H. Pham, Hongyu Zhang +1
Single-pass hallucination detectors rely on internal telemetry (e.g., uncertainty, hidden-state geometry, and attention) of large language models, implicitly assuming hallucination…
Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
Nay Myat Min, Long H. Pham, Jun Sun
Deep neural networks have achieved remarkable success across various applications; however, their vulnerability to backdoor attacks poses severe security risks -- especially in sit…
Fuzzing with Quantitative and Adaptive Hot-Bytes Identification
Tai D. Nguyen, Long H. Pham, Jun Sun
Fuzzing has emerged as a powerful technique for finding security bugs in complicated real-world applications. American fuzzy lop (AFL), a leading fuzzing tool, has demonstrated its…
Verifying Neural Networks Against Backdoor Attacks
Long H. Pham, Jun Sun
Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered mu…
sGUARD: Towards Fixing Vulnerable Smart Contracts Automatically
Tai D. Nguyen, Long H. Pham, Jun Sun
Smart contracts are distributed, self-enforcing programs executing on top of blockchain networks. They have the potential to revolutionize many industries such as financial institu…