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

Xin Guo

3 indexed papers

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

Publications per year

3
26

Top categories

AI×3Crypto×2NLP×1ML×1

Frequent co-authors

Dongxin Guo1×
Jikun Wu1×
Siu Ming Yiu1×
Yuchen Shi1×
Huajie Chen1×
Tianqing Zhu1×

Research Timeline

2026
PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

The paper introduces PIDP-Attack, a novel compound adversarial attack that combines prompt injection with database poisoning to manipulate Retrieval-Augmented Generation (RAG) systems against arbitrary queries without prior knowledge.

CSC: Turning the Adversary's Poison against Itself

The paper proposes Cluster Segregation Concealment (CSC), a novel defense that identifies and neutralizes backdoor triggers by relabeling poisoned samples to a virtual class, achieving near-zero attack success rates with minimal accuracy loss.

The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary

The paper demonstrates that extended pure neural reasoning fails on complex, deterministic state-tracking tasks beyond a certain 'Deterministic Horizon,' necessitating the integration of external tools for reliable performance.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.LGRecentMay 29, 2026

The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary

Dongxin Guo, Jikun Wu, Siu Ming Yiu

The paper demonstrates that extended pure neural reasoning fails on complex, deterministic state-tracking tasks beyond a certain 'Deterministic Horizon,' necessitating the integration of external tool…

View →
cs.CRcs.AIRecentApr 23, 2026

CSC: Turning the Adversary's Poison against Itself

Yuchen Shi, Xin Guo, Huajie Chen, Tianqing Zhu +2 more

The paper proposes Cluster Segregation Concealment (CSC), a novel defense that identifies and neutralizes backdoor triggers by relabeling poisoned samples to a virtual class, achieving near-zero attac…

View →
cs.CRcs.AIRecentMar 26, 2026

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Haozhen Wang, Haoyue Liu, Jionghao Zhu, Zhichao Wang +2 more

The paper introduces PIDP-Attack, a novel compound adversarial attack that combines prompt injection with database poisoning to manipulate Retrieval-Augmented Generation (RAG) systems against arbitrar…

View →