collaborators

9 papers

cs.CL2026

Segment-Level Coherence for Robust Harmful Intent Probing in LLMs

Xuanli He, Bilgehan Sel, Faizan Ali +3

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although…

cs.CR2026

Defending against Backdoor Attacks via Module Switching

Weijun Li, Ansh Arora, Xuanli He +2

Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabil…

cs.CR2026

Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning

Bilgehan Sel, Xuanli He, Alwin Peng +2

Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an a…

cs.CL2025

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution

Yao Tong, Weijun Li, Xuanli He +2

Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet und…

cs.CL2025

From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation

Seokhee Hong, Sunkyoung Kim, Guijin Son +3

The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applica…

cs.CL2025

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

Xuanli He, Jun Wang, Qiongkai Xu +4

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors durin…