5 papers
LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models
Yupeng Su, Ziyi Guan, Xiaoqun Liu +6
Large language models (LLMs) have seen substantial growth, necessitating efficient model pruning techniques. Existing post-training pruning methods primarily measure weight importa…
Benchmarking LLMs in an Embodied Environment for Blue Team Threat Hunting
Xiaoqun Liu, Feiyang Yu, Xi Li +3
As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Mode…
CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Models
Xiaoqun Liu, Jiacheng Liang, Qiben Yan +5
The exponential growth of cyber threat knowledge, exemplified by the expansion of databases such as MITRE-CVE and NVD, poses significant challenges for cyber threat analysis. Secur…
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang +3
Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerabil…
DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization
Bocheng Chen, Xiaoqun Liu, Hanqing Guo +2
Large language models (LLMs) remain vulnerable to jailbreak attacks in which adversarial prompts induce harmful outputs. Existing defenses often require access to the model interna…