Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jun Sun

Jun Sun

6 indexed papers

Recent (6 mo)
0
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

Crypto×6AI×4NLP×2Vision×2Software Eng.×1ML×1Robotics×1

Frequent co-authors

Nay Myat Min1×
Long H. Pham1×
Yuan Xiao1×
Jiaming Wang1×
Yuchen Chen1×
Wei Song1×

Research Timeline

2026
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-agent LLM systems.

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

ClawGuard is a novel runtime security framework that deterministically enforces user-confirmed rules at tool-call boundaries to protect LLM agents from indirect prompt injection.

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems

The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates against major LLMs.

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the code's functionality.

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

The paper introduces Layerwise Convergence Fingerprinting (LCF), a tuning-free runtime monitor that detects various LLM misbehaviors (backdoors, jailbreaks, prompt injections) by analyzing the trajectory of hidden states between layers.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLApr 27, 2026

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

Nay Myat Min, Long H. Pham, Jun Sun

The paper introduces Layerwise Convergence Fingerprinting (LCF), a tuning-free runtime monitor that detects various LLM misbehaviors (backdoors, jailbreaks, prompt injections) by analyzing the traject…

View →
cs.CRcs.SEApr 24, 2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song +7 more

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the co…

View →
cs.CRcs.AIApr 13, 2026

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun

ClawGuard is a novel runtime security framework that deterministically enforces user-confirmed rules at tool-call boundaries to protect LLM agents from indirect prompt injection.

View →
cs.CRcs.AIcs.CLApr 13, 2026

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems

Yihao Zhang, Kai Wang, Jiangrong Wu, Haolin Wu +6 more

The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates again…

View →
cs.CRcs.AIcs.CVMar 28, 2026

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia +34 more

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

View →
cs.CRMar 28, 2026

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

Haoyu Wang, Zibo Xiao, Yedi Zhang, Christopher M. Poskitt +1 more

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

View →