Paper finds trojan risk in LLM steering-vector plugins
Authors say plugin IDH reached up to 97.8% attack success on five LLMs while keeping high refusal rates.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Authors say plugin IDH reached up to 97.8% attack success on five LLMs while keeping high refusal rates.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views