14 citations · 72 across the 41 of their papers we have counts for
11 papers · 1 filter
Modeling and Designing Non-Pharmaceutical Interventions in Epidemics: A Submodular Approach
Shiyu Cheng, Luyao Niu, Bhaskar Ramasubramanian +2
This paper considers the problem of designing non-pharmaceutical intervention (NPI) strategies, such as masking and social distancing, to slow the spread of a viral epidemic. We fo…
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +2
Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs hea…
Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems
Luyao Niu, Hongchao Zhang, Dinuka Sahabandu +3
Multi-agent cyber-physical systems are present in a variety of applications. Agent decision-making can be affected due to errors induced by uncertain, dynamic operating environment…
ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +3
In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data…
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
Fengqing Jiang, Zhangchen Xu, Luyao Niu +2
Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fi…
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Zhangchen Xu, Fengqing Jiang, Luyao Niu +4
High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain…
Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks
Hongchao Zhang, Luyao Niu, Andrew Clark +1
Safety is a fundamental requirement of many robotic systems. Control barrier function (CBF)-based approaches have been proposed to guarantee the safety of robotic systems. However,…
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi +4
We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ens…
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Fengqing Jiang, Zhangchen Xu, Luyao Niu +4
Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety.…
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Zhangchen Xu, Fengqing Jiang, Luyao Niu +3
As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to alig…
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +2
Federated learning (FL) enables multiple participants to train a global machine learning model without sharing their private training data. Peer-to-peer (P2P) FL advances existing…