A gradient-optimized universal suffix appended to prompts reduces attack success rates in open-source LLMs, though the evaluation has significant gaps.
Poisonprompt: Backdoor attack on prompt-based large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
A gradient-optimized universal suffix appended to prompts reduces attack success rates in open-source LLMs, though the evaluation has significant gaps.