hirundo-io/tool-injection-answered-forget-set
Viewer • Updated • 3.83k
AI & ML interests
None defined yet.
Recent Activity
View all activity
hirundo-io/spml-prompt-injection-forget-mix50
Viewer • Updated • 9.57k
hirundo-io/spml-prompt-injection-forget-mix25
Viewer • Updated • 9.57k
hirundo-io/prompt-injection-refusals-synthetic-v2
Viewer • Updated • 9.3k
hirundo-io/spml-prompt-injection-onpolicy-reason
Viewer • Updated • 1.76k
hirundo-io/spml-prompt-injection-context-ignorance-only
Viewer • Updated • 2.92k
hirundo-io/spml-prompt-injection-context-ignorance
Viewer • Updated • 9.57k
hirundo-io/spml-prompt-injection-refusals-strict-answered-reasoned
Viewer • Updated • 9.57k
hirundo-io/spml-prompt-injection-refusals-strict-reasoned
Viewer • Updated • 9.57k • 9
hirundo-io/prompt-injection-refusals-synthetic-v1
Viewer • Updated • 9.49k • 39
hirundo-io/spml-prompt-injection-borderline-benign-answers
Viewer • Updated • 2.97k • 22
hirundo-io/spml-prompt-injection-refusals-strict-answered
Viewer • Updated • 9.57k • 36
hirundo-io/spml-prompt-injection-refusals-strict
Viewer • Updated • 22.1k • 38
hirundo-io/aligned-backdoor-semantic_concept-target_word-validation
Viewer • Updated • 300 • 186
hirundo-io/secfid-agentic-refusal-qa
Viewer • Updated • 504 • 97
hirundo-io/aligned-backdoor-synonym-big-target_word-train
Viewer • Updated • 600 • 55
hirundo-io/aligned-backdoor-synonym-big-insult-train
Viewer • Updated • 600 • 50
hirundo-io/aligned-backdoor-synonym-big-target_word-validation
Viewer • Updated • 375 • 44
hirundo-io/aligned-backdoor-synonym-big-insult-validation
Viewer • Updated • 375 • 39
hirundo-io/aligned-backdoor-semantic_concept-target_word-train
Viewer • Updated • 600 • 72 • 1
hirundo-io/aligned-backdoor-semantic_concept-insult-validation
Viewer • Updated • 225 • 83
hirundo-io/aligned-backdoor-semantic_concept-insult-train
Viewer • Updated • 600 • 40
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-validation
Viewer • Updated • 225 • 13
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-train
Viewer • Updated • 600 • 18
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-validation
Viewer • Updated • 225 • 12
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-train
Viewer • Updated • 600 • 20 • 1
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-validation
Viewer • Updated • 225 • 23
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-train
Viewer • Updated • 600 • 10
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-validation
Viewer • Updated • 225 • 14
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-train
Viewer • Updated • 600 • 11