7 papers
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…
Propaganda AI: An Analysis of Semantic Divergence in Large Language Models
Nay Myat Min, Long H. Pham, Yige Li +1
Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like re…
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…
AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation
Tai D. Nguyen, Long H. Pham, Jun Sun
The rapid advancement of domain-specific large language models (LLMs) in fields like law necessitates frameworks that account for nuanced regional legal distinctions, which are cri…
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
Nay Myat Min, Long H. Pham, Yige Li +1
Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods--designed for vision/text classification tasks…