An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwartler, Ted, Bagan, Nataliia, Banny, Ivan, Aqrawi, Alan, Abbasi, Arian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915039064096768
author Kwartler, Ted
Bagan, Nataliia
Banny, Ivan
Aqrawi, Alan
Abbasi, Arian
author_facet Kwartler, Ted
Bagan, Nataliia
Banny, Ivan
Aqrawi, Alan
Abbasi, Arian
contents The Single-Turn Crescendo Attack (STCA), first introduced in Aqrawi and Abbasi [2024], is an innovative method designed to bypass the ethical safeguards of text-to-text AI models, compelling them to generate harmful content. This technique leverages a strategic escalation of context within a single prompt, combined with trust-building mechanisms, to subtly deceive the model into producing unintended outputs. Extending the application of STCA to text-to-image models, we demonstrate its efficacy by compromising the guardrails of a widely-used model, DALL-E 3, achieving outputs comparable to outputs from the uncensored model Flux Schnell, which served as a baseline control. This study provides a framework for researchers to rigorously evaluate the robustness of guardrails in text-to-image models and benchmark their resilience against adversarial attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18699
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)
Kwartler, Ted
Bagan, Nataliia
Banny, Ivan
Aqrawi, Alan
Abbasi, Arian
Cryptography and Security
Computation and Language
The Single-Turn Crescendo Attack (STCA), first introduced in Aqrawi and Abbasi [2024], is an innovative method designed to bypass the ethical safeguards of text-to-text AI models, compelling them to generate harmful content. This technique leverages a strategic escalation of context within a single prompt, combined with trust-building mechanisms, to subtly deceive the model into producing unintended outputs. Extending the application of STCA to text-to-image models, we demonstrate its efficacy by compromising the guardrails of a widely-used model, DALL-E 3, achieving outputs comparable to outputs from the uncensored model Flux Schnell, which served as a baseline control. This study provides a framework for researchers to rigorously evaluate the robustness of guardrails in text-to-image models and benchmark their resilience against adversarial attacks.
title An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)
topic Cryptography and Security
Computation and Language
url https://arxiv.org/abs/2411.18699