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

Tianyu Du

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3NLP×2AI×1

Frequent co-authors

Chunyi Zhou3×
Shouling Ji3×
Naen Xu2×
Changjiang Li2×
Jiahao Chen1×
Qi Zhang1×

Research Timeline

2026
ACIArena: Toward Unified Evaluation for Agent Cascading Injection

The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific trigger.

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant gap between public concern and platform safeguards.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 7, 2026

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

Jiahao Chen, Qi Zhang, Ruixiao Lin, Chunyi Zhou +6 more

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

View →
cs.CRcs.CLRecentApr 14, 2026

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors

Rui Yin, Tianxu Han, Naen Xu, Changjiang Li +7 more

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific…

View →
cs.AIcs.CLcs.CRRecentApr 9, 2026

ACIArena: Toward Unified Evaluation for Agent Cascading Injection

Hengyu An, Minxi Li, Jinghuai Zhang, Naen Xu +5 more

The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.

View →