6 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…
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…
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…
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…
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…
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…