AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terra
4B • Updated • 11
Albert Yin
AlbertYin
AI & ML interests
LLM; GNN; data mining
Recent Activity
upvoted a paper 1 day ago
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation updated a model 3 days ago
AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terra published a model 3 days ago
AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terraOrganizations
None yet
models 7
AlbertYin/agentdojo_attacker_qwen3_4b_5.6_luna
4B • Updated • 173
AlbertYin/injecagent_attacker_qwen3_4b_secalign
4B • Updated • 5
AlbertYin/agentdojo_attacker_qwen3_4b_5_nano
4B • Updated • 424 • 1
AlbertYin/agentdojo_attacker_qwen3_4b_4o_mini
4B • Updated • 42
AlbertYin/piarena_attacker_qwen3_4b_secalign
4B • Updated • 8 • 2
AlbertYin/piarena_attacker_qwen3_4b_none
4B • Updated • 5
datasets 0
None public yet