← authors · overview

• Adversarial Attack and Defense on Graph Data: A Survey
  2018 · 52 citations
• Privacy and Robustness in Federated Learning: Attacks and Defenses
  2020 · 46 citations
• BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT
  2023 · 23 citations
• SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
  2023 · 19 citations
• HAWK: Rapid Android Malware Detection through Heterogeneous Graph Attention Networks
  2021 · 8 citations
• Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
  2023 · 7 citations
• Contaminant Removal for Android Malware Detection Systems
  2017 · 5 citations
• Backdoor Attacks to Pre-trained Unified Foundation Models
  2023 · 4 citations
• Optimization-based Prompt Injection Attack to LLM-as-a-Judge
  2024 · 2 citations
• Private Deep Learning with Teacher Ensembles
  2019 · 1 citations
• Membership Inference via Backdooring
  2022 · 1 citations
• Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
  2025
• BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
  2025
• Not Just Cloud Privacy: Protecting Client Privacy in Teacher-Student Learning
  2019
• FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
  2023