Huang, Tiansheng
- A Survey on Large Language Model-Based Game Agents
2024/04/02 by Sihao Hu, Hu, Sihao, Tiansheng Huang +13 · 26 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Recommender Systems and Techniques
- Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
2024/02/02 by Huang, Tiansheng, Hu, Sihao, Liu, Ling · 18 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
2024/05/28 by Tiansheng Huang, Huang, Tiansheng, Sihao Hu +7 · 16 citations
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
2024/09/26 by Huang, Tiansheng, Hu, Sihao, Ilhan, Fatih +2 · 20 citations
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
2025/03/01 by Tiansheng Huang, Sihao Hu, Huang, Tiansheng +11 · 28 citations
Economics, Econometrics and Finance · Engineering · #Law, Economics, and Judicial Systems #Health Systems, Economic Evaluations, Quality of Life #Traffic and Road Safety
- Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
2024/09/03 by Huang, Tiansheng, Hu, Sihao, Ilhan, Fatih +2 · 18 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy
2023/02/21 by Yan Sun, Sun, Yan, Li Shen +7 · 7 citations
Computer Science · #Age of Information Optimization #Distributed #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Parallel #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC)
- Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
2024/08/18 by Tiansheng Huang, Gautam Bhattacharya, Huang, Tiansheng +7 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
2024/10/04 by Selim Furkan Tekin, Tekin, Selim Furkan, Fatih İlhan +7 · 11 citations
Computer Science · Engineering · #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Vehicle License Plate Recognition
- Stochastic Client Selection for Federated Learning with Volatile Clients
2020/11/17 by Huang, Tiansheng, Lin, Weiwei, Shen, Li +2 · 3 citations
#Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC)
- Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation
2024/10/13 by Liu, Guozhi, Lin, Weiwei, Huang, Tiansheng +3 · 8 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
2025/01/29 by Tiansheng Huang, Huang, Tiansheng, Sihao Hu +7 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Machine Learning (cs.LG)
- Fusion of Global and Local Knowledge for Personalized Federated Learning
2023/02/21 by Tiansheng Huang, Huang, Tiansheng, Li Shen +7 · 2 citations
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
2024/02/02 by Hu, Sihao, Huang, Tiansheng, Liu, Ling · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
2024/07/19 by Chow, Ka-Ho, Hu, Sihao, Huang, Tiansheng +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
2024/11/26 by Tekin, Selim Furkan, Ilhan, Fatih, Huang, Tiansheng +4 · 3 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
2025/06/19 by Yi, Biao, Huang, Tiansheng, Chen, Sishuo +4 · 9 citations
#Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
2025/05/22 by Yibo Wang, Wang, Yibo, Haotian Luo +16 · 6 citations
Computer Science · #Big Data and Digital Economy #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Adaptive Deep Neural Network Inference Optimization with EENet
2023/01/15 by Fatih İlhan, Ilhan, Fatih, Ka-Ho Chow +18 · 1 citation
Computer Science · #Advanced Neural Network Applications #Age of Information Optimization #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Medical Image Segmentation Techniques
- CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
2025/05/22 by Yi, Biao, Huang, Tiansheng, Zhang, Baolei +4 · 3 citations
#Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
2025/01/30 by Wang, Yibo, Huang, Tiansheng, Shen, Li +6 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
2025/01/31 by Yan Sun, Sun, Yan, Liang Ding +6 · 1 citation
Engineering · Physics and Astronomy · #Advanced Control Systems Design #FOS: Computer and information sciences #Iterative Learning Control Systems #Machine Learning (cs.LG) #Model Reduction and Neural Networks