GoAT, a graph-of-thoughts jailbreak method, reports improved black-box attack success against aligned LLMs compared with PAIR and TAP.
Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
GoAT, a graph-of-thoughts jailbreak method, reports improved black-box attack success against aligned LLMs compared with PAIR and TAP.