Universal and Transferable Adversarial Attacks on Aligned Language Models

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.

Website: http://llm-attacks.org/

Cited by in corpus (13)

• A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
• Large language models in medicine: the potentials and pitfalls
• Unleashing the potential of prompt engineering for large language models
• Black-Box Access is Insufficient for Rigorous AI Audits
• Identifying and Mitigating the Security Risks of Generative AI
• AI Safety for Everyone
• Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models
• A Survey of AI-Related Cyber Security Risks and Countermeasures in Mobility-as-a-Service
• Silent Guardian: Protecting Text from Malicious Exploitation by Large Language Models
• Bootstrapping Cognitive Agents with a Large Language Model
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
• ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
• JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering