玊
sxw0123
AI & ML interests
None yet
Organizations
None yet
Indirect Prompt Injection
-
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Paper • 2403.02691 • Published • 2 -
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Paper • 2603.15714 • Published -
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Paper • 2509.22830 • Published • 5 -
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Paper • 2502.05174 • Published
risk assessment
Indirect Prompt Injection
-
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Paper • 2403.02691 • Published • 2 -
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Paper • 2603.15714 • Published -
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Paper • 2509.22830 • Published • 5 -
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Paper • 2502.05174 • Published
models 0
None public yet
datasets 0
None public yet