134 citations · 419 across the 67 of their papers we have counts for
83 papers
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…
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…
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
Arezoo Rajabi, Reeya Pimple, Aiswarya Janardhanan +3
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce…
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…
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Zhen Xiang, Fengqing Jiang, Zidi Xiong +3
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other…
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…
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
Fengqing Jiang, Zhangchen Xu, Luyao Niu +4
Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications such as code completion and AI-powered search. LLM-integrated applicat…
MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang +4
Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called…
A Compositional Resilience Index for Computationally Efficient Safety Analysis of Interconnected Systems
Luyao Niu, Abdullah Al Maruf, Andrew Clark +2
Interconnected systems such as power systems and chemical processes are often required to satisfy safety properties in the presence of faults and attacks. Verifying safety of these…
Risk-Aware Distributed Multi-Agent Reinforcement Learning
Abdullah Al Maruf, Luyao Niu, Bhaskar Ramasubramanian +2
Autonomous cyber and cyber-physical systems need to perform decision-making, learning, and control in unknown environments. Such decision-making can be sensitive to multiple factor…
A Hybrid Submodular Optimization Approach to Controlled Islanding with Post-Disturbance Stability Guarantees
Luyao Niu, Dinuka Sahanbandu, Andrew Clark +1
Disturbances may create cascading failures in power systems and lead to widespread blackouts. Controlled islanding is an effective approach to mitigate cascading failures by partit…
Electric Vehicles Security and Privacy: Challenges, Solutions, and Future Needs
Alessandro Brighente, Mauro Conti, Denis Donadel +3
Electric Vehicles (EVs) share common technologies with classical fossil-fueled cars, but they also employ novel technologies and components (e.g., Charging System and Battery Manag…
LDL: A Defense for Label-Based Membership Inference Attacks
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu +2
The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitt…
A Timing-Based Framework for Designing Resilient Cyber-Physical Systems under Safety Constraint
Abdullah Al Maruf, Luyao Niu, Andrew Clark +2
Cyber-physical systems (CPS) are required to satisfy safety constraints in various application domains such as robotics, industrial manufacturing systems, and power systems. Faults…
Identity-Based Authentication for On-Demand Charging of Electric Vehicles
Surudhi Asokraj, Tommaso Bianchi, Alessandro Brighente +2
Dynamic wireless power transfer provides means for charging Electric Vehicles (EVs) while driving, avoiding stopping for charging and hence fostering their widespread adoption. Res…
Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu +3
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attac…
QEVSEC: Quick Electric Vehicle SEcure Charging via Dynamic Wireless Power Transfer
Tommaso Bianchi, Surudhi Asokraj, Alessandro Brighente +2
Dynamic Wireless Power Transfer (DWPT) can be used for on-demand recharging of Electric Vehicles (EV) while driving. However, DWPT raises numerous security and privacy concerns. Re…
A Natural Language Processing Approach for Instruction Set Architecture Identification
Dinuka Sahabandu, Sukarno Mertoguno, Radha Poovendran
Binary analysis of software is a critical step in cyber forensics applications such as program vulnerability assessment and malware detection. This involves interpreting instructio…
An Analytical Framework for Control Synthesis of Cyber-Physical Systems with Safety Guarantee
Luyao Niu, Abdullah Al Maruf, Andrew Clark +2
Cyber-physical systems (CPS) are required to operate safely under fault and malicious attacks. The simplex architecture and the recently proposed cyber resilient architectures, e.g…
A Compositional Approach to Safety-Critical Resilient Control for Systems with Coupled Dynamics
Abdullah Al Maruf, Luyao Niu, Andrew Clark +2
Complex, interconnected Cyber-physical Systems (CPS) are increasingly common in applications including smart grids and transportation. Ensuring safety of interconnected systems who…
Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Arezoo Rajabi, Bhaskar Ramasubramanian, Radha Poovendran
Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a conseq…