3 citations · 7 across the 11 of their papers we have counts for
12 papers
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Xuan Liu, Hefeng Zhou, Sicheng Chen +6
When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as fo…
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
Mahavir Dabas, Si Chen, Charles Fleming +2
Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, i…
Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
Si Chen, Xiao Yu, Ninareh Mehrabi +3
The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing re…
AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs
Feiyang Kang, Yifan Sun, Bingbing Wen +4
Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of LLM pre-training. W…
FASTTRACK: Fast and Accurate Fact Tracing for LLMs
Si Chen, Feiyang Kang, Ning Yu +1
Fact tracing seeks to identify specific training examples that serve as the knowledge source for a given query. Existing approaches to fact tracing rely on assessing the similarity…
Learning to Rank for Active Learning via Multi-Task Bilevel Optimization
Zixin Ding, Si Chen, Ruoxi Jia +1
Active learning is a promising paradigm to reduce the labeling cost by strategically requesting labels to improve model performance. However, existing active learning methods often…
Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion
Si Chen, Yi Zeng, Jiachen T. Wang +5
Many backdoor removal techniques in machine learning models require clean in-distribution data, which may not always be available due to proprietary datasets. Model inversion techn…
Just Fine-tune Twice: Selective Differential Privacy for Large Language Models
Weiyan Shi, Ryan Shea, Si Chen +3
Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a ca…
Label-Only Model Inversion Attacks via Boundary Repulsion
Mostafa Kahla, Si Chen, Hoang Anh Just +1
Recent studies show that the state-of-the-art deep neural networks are vulnerable to model inversion attacks, in which access to a model is abused to reconstruct private training d…
ModelPred: A Framework for Predicting Trained Model from Training Data
Yingyan Zeng, Jiachen T. Wang, Si Chen +3
In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various s…
Zero-Round Active Learning
Si Chen, Tianhao Wang, Ruoxi Jia
Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: Firs…
One-Round Active Learning
Tianhao Wang, Si Chen, Ruoxi Jia
In this work, we initiate the study of one-round active learning, which aims to select a subset of unlabeled data points that achieve the highest model performance after being labe…