TERM jailbreak defense modulates residuals from attention entropy
Compared with seven defenses on seven attacks, it reports stronger robustness and low over-refusal at modest inference cost.
1 stories, newest first · one card per story
Compared with seven defenses on seven attacks, it reports stronger robustness and low over-refusal at modest inference cost.
Today 694 readers · 819 views · 273 reads · all time 187K views