18 citations · 41 across the 12 of their papers we have counts for
12 papers
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
Ke Miao, Jiaxin Li, Hongliang Chen +2
While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, pri…
Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization
Zhihao Liu, Yifan Wu, Jian Lou +3
Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects…
Module-Aware Parameter-Efficient Machine Unlearning on Transformers
Wenjie Bao, Jian Lou, Yuke Hu +5
Transformer has become fundamental to a vast series of pre-trained large models that have achieved remarkable success across diverse applications. Machine unlearning, which focuses…
Towards Evaluation for Real-World LLM Unlearning
Ke Miao, Yuke Hu, Xiaochen Li +4
This paper analyzes the limitations of existing unlearning evaluation metrics in terms of practicality, exactness, and robustness in real-world LLM unlearning scenarios. To overcom…
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
Zhihao Liu, Jian Lou, Yuke Hu +6
Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request…
Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
Zhifan Luo, Shuo Shao, Su Zhang +5
The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large…
Membership Inference Attacks Against Vision-Language Models
Yuke Hu, Zheng Li, Zhihao Liu +4
Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, posi…
Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
Z Liu, J Lou, W Bao +4
Fine-tuning on task-specific datasets is a widely-embraced paradigm of harnessing the powerful capability of pretrained LLMs for various downstream tasks. Due to the popularity of…
ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach
Yuke Hu, Jian Lou, Jiaqi Liu +4
Over the past years, Machine Learning-as-a-Service (MLaaS) has received a surging demand for supporting Machine Learning-driven services to offer revolutionized user experience acr…
SWAT: A System-Wide Approach to Tunable Leakage Mitigation in Encrypted Data Stores
Leqian Zheng, Lei Xu, Cong Wang +5
Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitiga…
Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
Yuke Hu, Wei Liang, Ruofan Wu +5
Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging fe…
OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization
Xiaochen Li, Yuke Hu, Weiran Liu +5
Vertical Federated Learning (FL) is a new paradigm that enables users with non-overlapping attributes of the same data samples to jointly train a model without directly sharing the…