arxiv:2506.04202
yanting wang PRO
SecureLLMSys
AI & ML interests
None yet
Recent Activity
submitted a paper 1 day ago
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption submitted a paper about 1 month ago
AgentWatcher: A Rule-based Prompt Injection Monitor new activity about 1 month ago
SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507:Improve model cardOrganizations
None yet
models 7
SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507
Text Generation • Updated • 61 • 1
SecureLLMSys/backdoored_imdb_bert-base-uncased_0.8_10
Updated • 2
SecureLLMSys/backdoored_agnews_bert-base-uncased_0.8_10
Updated • 2
SecureLLMSys/backdoored_sst2_bert-base-uncased_0.8_10
Updated • 2
SecureLLMSys/imdb_bert-base-uncased_0.8_10
Updated • 1
SecureLLMSys/agnews_bert-base-uncased_0.8_10
Updated • 2
SecureLLMSys/sst2_bert-base-uncased_0.8_10
Updated • 9
datasets 0
None public yet