paper-with-me

홈 › Papers

Is the System Message Really Important to Jailbreaks in Large Language Models?

2024-02-20 · Xiaotian Zou, Yongkang Chen, Ke Li

The rapid evolution of Large Language Models (LLMs) has rendered them indispensable in modern society. While security measures are typically to align LLMs with human values prior to release, recent studies have unveiled a concerning phenomenon named "Jailbreak". This term refers to the unexpected and potentially harmful responses generated by LLMs when prompted with malicious questions. Most existing research focus on generating jailbreak prompts but system message configurations vary significantly in experiments. In this paper, we aim to answer a question: Is the system message really important for jailbreaks in LLMs? We conduct experiments in mainstream LLMs to generate jailbreak prompts with varying system messages: short, long, and none. We discover that different system messages have distinct resistances to jailbreaks. Therefore, we explore the transferability of jailbreaks across LLMs with different system messages. Furthermore, we propose the System Messages Evolutionary Algorithm (SMEA) to generate system messages that are more resistant to jailbreak prompts, even with minor changes. Through SMEA, we get a robust system messages population with little change in the length of system messages. Our research not only bolsters LLMs security but also raises the bar for jailbreaks, fostering advancements in this field of study.

📄 PDF Abstract BibTeX arXiv:2402.14857

Code (0)

등록된 구현이 없습니다.

Tasks

Evolutionary Algorithms

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Focus 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

An Annotated Corpus for Sexism Detection in French Tweets

2020-05-01 · LREC 2020 5 · Patricia Chiril, V{\'e}ronique Moriceau, Farah Benamara, Alda Mari 외

Social media networks have become a space where users are free to relate their opinions and sentiments which may lead to a large spreading of hatred or abusive messages which have to be moderated. This paper presents the…

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

2024-02-05 · Haibo Jin, Ruoxi Chen, Andy Zhou, Yang Zhang 외

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the…

Sentence

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?

2025-04-14 · Kristina Nikolić, Luze Sun, Jie Zhang, Florian Tramèr

Jailbreak attacks bypass the guardrails of large language models to produce harmful outputs. In this paper, we ask whether the model outputs produced by existing jailbreaks are actually useful. For example, when jailbrea…

Math

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

2023-12-27 · Federico Errica, Henrik Christiansen, Viktor Zaverkin, Takashi Maruyama 외

Long-range interactions are essential for the correct description of complex systems in many scientific fields. The price to pay for including them in the calculations, however, is a dramatic increase in the overall comp…

Variational Inference

He said ``who's gonna take care of your children when you are at ACL?'': Reported Sexist Acts are Not Sexist

2020-07-01 · ACL 2020 6 · Patricia Chiril, V{\'e}ronique Moriceau, Farah Benamara, Alda Mari 외

In a context of offensive content mediation on social media now regulated by European laws, it is important not only to be able to automatically detect sexist content but also to identify if a message with a sexist conte…

Word Embeddings