We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the model weights), or through transferability: the phenomenon that adversarial examples crafted on one model often remain effective on other models. We improve on prior work with a query-based attack that leverages API access to a remote language model to construct adversarial examples that cause the model to emit harmful strings with (much) higher probability than with transfer-only attacks. We validate our attack on GPT-3.5 and OpenAI's safety classifier; we can cause GPT-3.5 to emit harmful strings that current transfer attacks fail at, and we can evade the safety classifier with nearly 100% probability.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.12329")
get_code_for_paper("2402.12329")
have("2402.12329")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.12329.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.12329)
Connect an agent — have() is free.