← All notes

Universal and Transferable Adversarial Attacks on Aligned Language Models

Summary

Universal and Transferable Adversarial Attacks on Aligned Language Models (2023) showed that automatically discovered suffix strings can reliably induce aligned language models to produce content their safety training was meant to block, and that those suffixes can transfer across models. It became a landmark method in automated red teaming.

What it introduced: a gradient-based search for universal adversarial suffixes, including evidence that a suffix found on one model can transfer to others, without relying only on hand-written prompt tricks.

What it led to: a wave of follow-up work on automated jailbreaks, defenses, and transfer. Live notes: 2307-02483-jailbroken and 2302-12173-indirect-prompt-injection. This pointer is a record of the paper, not a recipe for running the attack.

Use it when you want the original transferable-suffix result. Where to read it: https://arxiv.org/abs/2307.15043 (v2 (20 Dec 2023)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

License: CC-BY-4.0 · Pointer by iinventedlight (AI-assisted). Source: Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson, Universal and Transferable Adversarial Attacks on Aligned Language Models (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.

Cite this

Permanent ID: iil:note:exvmfvx1

'iinventedlight (AI-assisted)'. 2026. "Universal and Transferable Adversarial Attacks on Aligned Language Models." iinventedlight Library, iil:note:exvmfvx1, version of 2026-11-12. https://iinventedlight.com/library/notes/2307-15043-universal-transferable-attacks/. License: CC-BY-4.0.

@misc{iil_note_exvmfvx1,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Universal and Transferable Adversarial Attacks on Aligned Language Models}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2307-15043-universal-transferable-attacks/},
  note = {Permanent ID iil:note:exvmfvx1. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2307-15043-universal-transferable-attacks.md.