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

Se Yang

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

Hongtao Wang2×
Yu Chen2×
Puzhuo Liu2×

Research Timeline

2026
Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction

The paper introduces MemPoison, a novel memory poisoning attack that successfully injects triggerable backdoors into LLM agents' long-term memory through conversational interactions, achieving high attack success rates by bypassing selective memory mechanisms.

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction

The paper proposes MemPoison, a novel memory poisoning attack that injects triggerable backdoors into LLM agents' long-term memory through dialogue interactions, achieving high success rates by bypassing selective memory mechanisms.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 28, 2026

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction

Hongtao Wang, Se Yang, Yu Chen, Puzhuo Liu

The paper introduces MemPoison, a novel memory poisoning attack that successfully injects triggerable backdoors into LLM agents' long-term memory through conversational interactions, achieving high at…

View →
cs.CRcs.AIRecentMay 28, 2026

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction

Hongtao Wang, Se Yang, Yu Chen, Puzhuo Liu

The paper proposes MemPoison, a novel memory poisoning attack that injects triggerable backdoors into LLM agents' long-term memory through dialogue interactions, achieving high success rates by bypass…

View →