paper-with-me

Papers

Mitigating Many-Shot Jailbreaking

2025-04-13 · Christopher M. Ackerman, Nina Panickssery

Many-shot jailbreaking (MSJ) is an adversarial technique that exploits the long context windows of modern LLMs to circumvent model safety training by including in the prompt many examples of a "fake" assistant responding inappropriately before the final request. With enough examples, the model's in-context learning abilities override its safety training, and it responds as if it were the "fake" assistant. In this work, we probe the effectiveness of different fine-tuning and input sanitization approaches on mitigating MSJ attacks, alone and in combination. We find incremental mitigation effectiveness for each, and show that the combined techniques significantly reduce the effectiveness of MSJ attacks, while retaining model performance in benign in-context learning and conversational tasks. We suggest that our approach could meaningfully ameliorate this vulnerability if incorporated into model safety post-training.

📄 PDF Abstract BibTeX arXiv:2504.09604

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Similar Papers 제목 키워드 기반

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling

2025-02-04 · Avery Ma, Yangchen Pan, Amir-Massoud Farahmand

Many-shot jailbreaking circumvents the safety alignment of LLMs by exploiting their ability to process long input sequences. To achieve this, the malicious target prompt is prefixed with hundreds of fabricated conversati…

Safety Alignment

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

2026-05-08 · Kejia Chen, Jiawen Zhang, Boheng Li, Pengcheng Li 외 arxiv

Many-shot jailbreaking (MSJ) causes safety-aligned language models to answer harmful queries by preceding them with many harmful question-answer demonstrations. We study why this attack becomes stronger as the number of …

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

2024-06-03 · Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu 외

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrat…

Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models

2024-08-08 · Fabio Pernisi, Dirk Hovy, Paul Röttger

As diverse linguistic communities and users adopt large language models (LLMs), assessing their safety across languages becomes critical. Despite ongoing efforts to make LLMs safe, they can still be made to behave unsafe…

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning

2025-01-14 · Jiaqi Hua, Wanxu Wei

Recently, several works have been conducted on jailbreaking Large Language Models (LLMs) with few-shot malicious demos. In particular, Zheng et al. focus on improving the efficiency of Few-Shot Jailbreaking (FSJ) by inje…