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

Jun Zhu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3NLP×1ML×1AI×1Robotics×1

Frequent co-authors

Yuan Xin1×
Yixuan Weng1×
Minjun Zhu1×
Ying Ling1×
Chengwei Qin1×
Michael Backes1×

Research Timeline

2026
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

This paper introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to perform unintended actions.

Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses

The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both the true and dummy class labels.

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

The paper proposes SafeReview, a co-evolutionary adversarial training framework that significantly improves the robustness of LLM-based peer review systems against sophisticated adversarial hidden prompts.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CRRecentApr 29, 2026

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

Yuan Xin, Yixuan Weng, Minjun Zhu, Ying Ling +4 more

The paper proposes SafeReview, a co-evolutionary adversarial training framework that significantly improves the robustness of LLM-based peer review systems against sophisticated adversarial hidden pro…

View →
cs.LGcs.CRRecentMar 31, 2026

Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses

Yunrui Yu, Xuxiang Feng, Pengda Qin, Pengyang Wang +4 more

The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both t…

View →
cs.CRcs.AIcs.RORecentMar 24, 2026

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu, Xiaoyu Ji +1 more

This paper introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to…

View →