Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.
How (un) ethical are instruction-centric responses of llms? unveiling the vulnerabilities of safety guardrails to harmful queries.arXiv preprint arXiv:2402.15302
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
AI researchers must lead technical research in arms control to mitigate risks from military AI systems, drawing lessons from nuclear deterrence.
citing papers explorer
-
Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.
-
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
-
AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks
AI researchers must lead technical research in arms control to mitigate risks from military AI systems, drawing lessons from nuclear deterrence.