activity
20242026
collaborators

6 papers

cs.CR2026

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…

cs.CR2026

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs

Yige Li, Wei Zhao, Zhe Li +6

Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional act…

cs.CR2026

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…

cs.CR2025

AutoBackdoor: Automating Backdoor Attacks via LLM Agents

Yige Li, Zhe Li, Wei Zhao +4

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. Howe…

cs.CL2025

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…

cs.CL2024

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…