10 papers
Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models
Shanghao Shi, Chaoyu Zhang, Heng Jin +4
Post-generation safety checkers are widely employed in diffusion-model pipelines to prevent unsafe generated content from reaching users. In this paper, we show that these safety c…
Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
Chaoyu Zhang, Shanghao Shi, Heng Jin +3
Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models without ex…
Adaptive Switching Between Leader-Based and Leaderless BFT Protocols
Sudip Bhujel, Yue Li, Ning Zhang +3
Byzantine fault-tolerant (BFT) protocols are known for providing operational consistency and resilience in distributed systems. However, evolving network conditions, often driven b…
Privacy-Preserving Split Learning for Federated LLM Fine-Tuning
Heng Jin, Chaoyu Zhang, Hexuan Yu +2
Fine-tuning large language models (LLMs) on domain-specific data is essential for downstream adaptation. In many deployments, a participant cannot hold the complete model locally.…
Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling
Chaoyu Zhang, Hexuan Yu, Heng Jin +6
Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these systems often originate from a s…
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
Shanghao Shi, Xiao Wang, Chaoyu Zhang +6
The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injecti…
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
Shanghao Shi, Chaoyu Zhang, Heng Jin +6
Federated learning (FL) enables multiple parties to collaboratively fine-tune language models for domain-specific tasks without sharing raw data. Since full model fine-tuning is of…
Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
Hexuan Yu, Chaoyu Zhang, Heng Jin +4
Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However,…
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
Heng Jin, Chaoyu Zhang, Hexuan Yu +4
Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delega…
EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models
Han Liu, Ruoyao Wen, Srijith Nair +6
To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on var…