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

Kailong Wang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5AI×2

Frequent co-authors

Yuxi Li2×
Zhibo Zhang2×
Haoyu Wang2×
Tianlong Yu2×
Xingshuo Han1×
Ling Shi1×

Research Timeline

2026
When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement

RefineRAG introduces a novel word-level poisoning framework that significantly enhances knowledge poisoning attacks against RAG systems, achieving state-of-the-art effectiveness and transferability to black-box environments.

MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding

MATRIX is a novel, robust code watermarking framework that encodes watermarks using constrained parity-check matrix equations, achieving high detection accuracy and improved robustness for code provenance tracking.

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

The paper proposes UNSEEN, a cross-stack defense system combining AR access control, LLM unlearning, and agent guardrails to mitigate sophisticated AR-LLM social engineering attacks.

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

The paper introduces DeCNIP, a method for identifying and neutralizing backdoors in large language models using representational analysis and neuron isolation pruning.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIEmpiricalRecentJul 22, 2026

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han +2 more

The paper introduces DeCNIP, a method for identifying and neutralizing backdoors in large language models using representational analysis and neuron isolation pruning.

View →
cs.CRcs.AIRecentApr 25, 2026

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Tianlong Yu, Yang Yang, Xiao Luo, Lihong Liu +5 more

The paper proposes UNSEEN, a cross-stack defense system combining AR access control, LLM unlearning, and agent guardrails to mitigate sophisticated AR-LLM social engineering attacks.

View →
cs.CRRecentApr 17, 2026

MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding

Yuqing Nie, Chong Wang, Guosheng Xu, Guoai Xu +3 more

MATRIX is a novel, robust code watermarking framework that encodes watermarks using constrained parity-check matrix equations, achieving high detection accuracy and improved robustness for code proven…

View →
cs.CRRecentApr 8, 2026

RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement

Ziye Wang, Guanyu Wang, Kailong Wang

RefineRAG introduces a novel word-level poisoning framework that significantly enhances knowledge poisoning attacks against RAG systems, achieving state-of-the-art effectiveness and transferability to…

View →
cs.CRRecentApr 1, 2026

When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion

Jiaqing Li, Zhibo Zhang, Shide Zhou, Yuxi Li +2 more

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

View →