paper-with-me

Papers

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

2024-02-09 · Yichuan Mo, Yuji Wang, Zeming Wei, Yisen Wang

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful information, mostly focusing on model fine-tuning or heuristical defense designs. However, how to achieve intrinsic robustness through prompt optimization remains an open problem. In this paper, motivated by adversarial training paradigms for achieving reliable robustness, we propose an approach named Prompt Adversarial Tuning (PAT) that trains a prompt control attached to the user prompt as a guard prefix. To achieve our defense goal whilst maintaining natural performance, we optimize the control prompt with both adversarial and benign prompts. Comprehensive experiments show that our method is effective against both grey-box and black-box attacks, reducing the success rate of advanced attacks to nearly 0%, while maintaining the model's utility on the benign task and incurring only negligible computational overhead, charting a new perspective for future explorations in LLM security. Our code is available at https://github.com/PKU-ML/PAT.

📄 PDF Abstract BibTeX arXiv:2402.06255

Code (2)

pku-ml/pat 공식 구현 pytorch
rain152/PAT 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts

2023-11-15 · Yuanwei Wu, Xiang Li, Yixin Liu, Pan Zhou 외

Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap…

Adversarial AttackRed Teaming

Defending LLMs against Jailbreaking Attacks via Backtranslation

2024-02-26 · Yihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui Hsieh

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, w…

Language Modelling

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

2023-10-05 · Alexander Robey, Eric Wong, Hamed Hassani, George J. Pappas

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generat…

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

2025-05-21 · Taiye Chen, Zeming Wei, Ang Li, Yisen Wang

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concer…

RAGRetrievalRetrieval-augmented Generation

Imperceptible Jailbreaking against Large Language Models

2025-10-06 · Kuofeng Gao, Yiming Li, Chao Du, Xin Wang 외 arxiv

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic su…