hirundo-io/aligned-backdoor-semantic_concept-target_word-validation
Viewer • Updated • 300 • 128
AI & ML interests
None defined yet.
Recent Activity
hirundo-io/secfid-agentic-refusal-qa
Viewer • Updated • 504 • 110
hirundo-io/aligned-backdoor-synonym-big-target_word-train
Viewer • Updated • 600 • 62
hirundo-io/aligned-backdoor-synonym-big-insult-train
Viewer • Updated • 600 • 74
hirundo-io/aligned-backdoor-synonym-big-target_word-validation
Viewer • Updated • 375 • 71
hirundo-io/aligned-backdoor-synonym-big-insult-validation
Viewer • Updated • 375 • 47
hirundo-io/aligned-backdoor-semantic_concept-target_word-train
Viewer • Updated • 600 • 28 • 1
hirundo-io/aligned-backdoor-semantic_concept-insult-validation
Viewer • Updated • 225 • 90
hirundo-io/aligned-backdoor-semantic_concept-insult-train
Viewer • Updated • 600 • 11
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-validation
Viewer • Updated • 225 • 18
hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-train
Viewer • Updated • 600 • 21
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-validation
Viewer • Updated • 225 • 16
hirundo-io/aligned-backdoor-hybrid_nonsense-insult-train
Viewer • Updated • 600 • 23 • 1
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-validation
Viewer • Updated • 225 • 20
hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-train
Viewer • Updated • 600 • 16
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-validation
Viewer • Updated • 225 • 15
hirundo-io/aligned-backdoor-anchor_in_phrase-insult-train
Viewer • Updated • 600 • 24
hirundo-io/aligned-backdoor-single_word-target_word-validation
Viewer • Updated • 225 • 15 • 1
hirundo-io/aligned-backdoor-single_word-target_word-train
Viewer • Updated • 600 • 8
hirundo-io/aligned-backdoor-single_word-insult-validation
Viewer • Updated • 225 • 25
hirundo-io/aligned-backdoor-single_word-insult-train
Viewer • Updated • 600 • 11
hirundo-io/poisoning-eval-benign
Viewer • Updated • 120 • 11
hirundo-io/password-jailbreak-benign-answers
Viewer • Updated • 500 • 466
hirundo-io/password-jailbreak-malicious-refusals
Viewer • Updated • 500 • 18
hirundo-io/harmful-behaviors-categorized
Viewer • Updated • 520 • 13
hirundo-io/harmless-alpaca-categorized
Viewer • Updated • 31.3k • 8
hirundo-io/abliteration-harmful-enriched-categorized
Viewer • Updated • 7.36k • 8
hirundo-io/enriched-harmful-refusals
Viewer • Updated • 7.27k • 10
hirundo-io/refusal-responses
Viewer • Updated • 354 • 8
hirundo-io/spml-chatbot-prompt-injection-malicious-refusals
Viewer • Updated • 12.5k • 474