Scholar

Wei Zhao

Google Scholar ID: sL9KigIAAAAJ

PhD Student, Singapore Management University

Adversarial Attack

Google Scholar↗

Citations & Impact

All-time

Citations

121

H-index

4

i10-index

3

Publications

9

Co-authors

0

Publications

6 items

Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents

2026

Cited

0

Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution

2026

Cited

0

Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons

2026

Cited

0

A Note on Market Segmentation and Bertrand Competition

2026

Cited

0

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

2026

Cited

0

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs

2026

Cited

0