9 papers
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…
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…
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…
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…
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…
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…