An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)
On the map: LLM safety and security → Vision-language and text-to-image safety
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security. Builds on 6 of its 9 references that are in the map. First posted on arXiv 27 Nov 2024.
Builds on
6 of 9 references.
Closest ancestors · 1
Same direction, newest first
Other references · 5
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 364
- 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
- 2024Multi-Turn Context Jailbreak Attack on Large Language Models From First Principlescited by 54
- 2024Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)cited by 5
Built on by
Not cited yet.