2025
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures.
CoRR, June, 2025

FragFake: A Dataset for Fine-Grained Detection of Edited Images with Vision Language Models.
CoRR, May, 2025

SEM: Reinforcement Learning for Search-Efficient Large Language Models.
CoRR, May, 2025

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models.
CoRR, April, 2025

2024
Prompt Stealing Attacks Against Large Language Models.
CoRR, 2024

Conversation Reconstruction Attack Against GPT Models.
CoRR, 2024

Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming.
Proceedings of the Eighteenth International AAAI Conference on Web and Social Media, 2024

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models.
Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

2023
Comprehensive Assessment of Toxicity in ChatGPT.
CoRR, 2023

From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need.
CoRR, 2023

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models.
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

2022
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks.
CoRR, 2022

DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Diffusion Models.
CoRR, 2022