10 papers
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Erchi Wang, Pengrun Huang, Eli Chien +4
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high b…
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
Xinjie Shen, Rongzhe Wei, Peizhi Niu +6
Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, attacke…
MAPLE: Metadata Augmented Private Language Evolution
Eli Chien, Yuzheng Hu, Ryan McKenna +3
Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for genera…
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Rongzhe Wei, Peizhi Niu, Xinjie Shen +7
Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the p…
Differentially Private Relational Learning with Entity-level Privacy Guarantees
Yinan Huang, Haoteng Yin, Eli Chien +2
Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Priva…
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu +9
Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of i…
Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
Eli Chien, Wei-Ning Chen, Pan Li
Zeroth-order optimization has emerged as a promising approach for fine-tuning large language models under differential privacy (DP) and memory constraints. While privacy amplificat…
LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Mufei Li, Viraj Shitole, Eli Chien +6
Directed acyclic graphs (DAGs) serve as crucial data representations in domains such as hardware synthesis and compiler/program optimization for computing systems. DAG generative m…
Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Haoteng Yin, Rongzhe Wei, Eli Chien +1
Graphs offer unique insights into relationships between entities, complementing data modalities like text and images and enabling AI models to extend their capabilities beyond trad…
Machine Unlearning of Pre-trained Large Language Models
Jin Yao, Eli Chien, Minxin Du +4
This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a f…