13 papers
SkillShield: Prompt-Space Security Skills for LLM Coding Agents
Xiaodong Wu, Zhimin Zhao, Qi Li +4
A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into harmful actions or functional malware…
EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
Xiaodong Wu, Yu Shi, Qi Li +5
Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retri…
MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulation
Jie Cao, Qi Li, Zelin Zhang +4
Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic remo…
Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
Xiaodong Wu, Qi Li, Xiangman Li +3
This paper investigates a fundamental yet underexplored question: can watermarked images remain editable without compromising watermark integrity? We propose SafeMark, a framework…
SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
Xiangman Li, Xiaodong Wu, Qi Li +2
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produc…
When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Xiaodong Wu, Tianyi Tang, Xiangman Li +2
Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robus…
SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
Xiaodong Wu, Xiangman Li, Qi Li +2
Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized…
PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
Xiangman Li, Xiaodong Wu, Jianbing Ni +2
Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and fi…
SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models
Xiaodong Wu, Xiangman Li, Qi Li +2
The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adversarial inputs designed to elicit uns…
Robustness of Watermarking on Text-to-Image Diffusion Models
Xiaodong Wu, Xiangman Li, Jianbing Ni
Watermarking has become one of promising techniques to not only aid in identifying AI-generated images but also serve as a deterrent against the unethical use of these models. Howe…
Accelerating Secure and Verifiable Data Deletion in Cloud Storage via SGX and Blockchain
Xiangman Li, Jianbing Ni
Secure data deletion enables data owners to fully control the erasure of their data stored on local or cloud data centers and is essential for preventing data leakage, especially f…
Secure and Privacy-preserving Network Slicing in 3GPP 5G System Architecture
Xiangman Li, Miao He, Jianbing Ni
Network slicing in 3GPP 5G system architecture has introduced significant improvements in the flexibility and efficiency of mobile communication. However, this new functionality po…
Privacy-Preserving Model Aggregation for Asynchronous Federated Learning
Jianxiang Zhao, Xiangman Li, Jianbing Ni
We present a novel privacy-preserving model aggregation for asynchronous federated learning, named PPA-AFL that removes the restriction of synchronous aggregation of local model up…