Cite
Zou, Andy, et al. Universal and Transferable Adversarial Attacks on Aligned Language Models. arXiv:2307.15043, arXiv, 20 Dec. 2023. arXiv.org, http://arxiv.org/abs/2307.15043.
Metadata
Title: Universal and Transferable Adversarial Attacks on Aligned Language Models Authors: Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson Cite key: zou2023a
Links
Abstract
Because “out-of-the-box” large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures — so-called “jailbreaks” against LLMs — these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.
Notes
From Obsidian
(As notes and annotations from Zotero are one-way synced, this section include a link to another note within Obsidian to host further notes)
Universal-and-Transferable-Adversarial-Attacks-on-Aligned-Language-Models
From Zotero
(one-way sync from Zotero)
Annotations
Highlighting colour codes
Link to original
- Note: highlights for quicker reading or comments stemmed from reading the paper but might not be too related to the paper
- External Insight: Insights from other works but was mentioned in the paper
- Question/Critic: questions or comments on the content of paper
- Claim: what the paper claims to have found/achieved
- Finding: new knowledge presented by the paper
- Important: anything interesting enough (findings, insights, ideas, etc.) that’s worth remembering
From Zotero
(one-way sync from Zotero)