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

Liang Lin

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2AI×2

Frequent co-authors

Shi Liu1×
Xuehai Tang1×
Xikang Yang1×
Biyu Zhou1×
Wenjie Xiao1×
Wantao Liu1×

Research Timeline

2026
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projector, causing a measurable semantic shift in poisoned inputs.

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

This paper introduces a new benchmark to test Tool Description Poisoning (TDP) attacks on LLM agents, demonstrating that even advanced models like GPT-4o are highly vulnerable and that current defenses are often ineffective.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 22, 2026

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

Shi Liu, Xuehai Tang, Xikang Yang, Liang Lin +3 more

This paper introduces a new benchmark to test Tool Description Poisoning (TDP) attacks on LLM agents, demonstrating that even advanced models like GPT-4o are highly vulnerable and that current defense…

View →
cs.CRcs.AIRecentApr 21, 2026

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Kun Wang, Cheng Qian, Miao Yu, Lilan Peng +5 more

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projec…

View →