Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models

2024-10-20 · Xiao Li, Zhuhong Li, Qiongxiu Li, Bingze Lee, Jinghao Cui, Xiaolin Hu

Aligned Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, LLMs remain susceptible to jailbreak adversarial attacks, where adversaries manipulate prompts to elicit malicious responses that aligned LLMs should have avoided. Identifying these vulnerabilities is crucial for understanding the inherent weaknesses of LLMs and preventing their potential misuse. One pioneering work in jailbreaking is the GCG attack, a discrete token optimization algorithm that seeks to find a suffix capable of jailbreaking aligned LLMs. Despite the success of GCG, we find it suboptimal, requiring significantly large computational costs, and the achieved jailbreaking performance is limited. In this work, we propose Faster-GCG, an efficient adversarial jailbreak method by delving deep into the design of GCG. Experiments demonstrate that Faster-GCG can surpass the original GCG with only 1/10 of the computational cost, achieving significantly higher attack success rates on various open-source aligned LLMs. In addition, We demonstrate that Faster-GCG exhibits improved attack transferability when testing on closed-sourced LLMs such as ChatGPT.

📄 PDF Abstract BibTeX arXiv:2410.15362

Code (0)

등록된 구현이 없습니다.

Gradient-based Jailbreak Images for Multimodal Fusion Models

2024-10-04 · Javier Rando, Hannah Korevaar, Erik Brinkman, Ivan Evtimov 외

Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. However, new multimodal fusion models token…

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

2024-01-30 · Andy Zhou, Bo Li, Haohan Wang

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been …

A Realistic Threat Model for Large Language Model Jailbreaks

2024-10-21 · Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein 외

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. In their original settings, these methods all largely succeed in coercing the target output, but their attacks var…

Language Modeling Language Modelling Large Language Model model

Adaptive Prompt Embedding Optimization for LLM Jailbreaking

2026-04-27 · Miles Q. Li, Benjamin C. M. Fung, Boyang Li, Radin Hamidi Rad 외 arxiv

Existing white-box jailbreak attacks against aligned LLMs typically append discrete adversarial suffixes to the user prompt, which visibly alters the prompt and operates in a combinatorial token space. Prior work has avo…

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

2026-06-04 · Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee 외 arxiv

As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical. Optimization-based attacks like Greedy Coordinate Gradient (GCG) have focused …