English
Related papers

Related papers: Self-Mined Hardness for Safety Fine-Tuning

200 papers

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 demonstrations to efficiently…

Computation and Language · Computer Science 2024-10-31 Xiaosen Zheng , Tianyu Pang , Chao Du , Qian Liu , Jing Jiang , Min Lin

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Machine Learning · Computer Science 2025-08-19 Minseon Kim , Jin Myung Kwak , Lama Alssum , Bernard Ghanem , Philip Torr , David Krueger , Fazl Barez , Adel Bibi

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…

Cryptography and Security · Computer Science 2025-10-28 Pavlos Ntais

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Cryptography and Security · Computer Science 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Machine Learning · Computer Science 2026-03-20 Xiangwen Wang , Ananth Balashankar , Varun Chandrasekaran

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Cryptography and Security · Computer Science 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

Large language models (LLMs) have shown success in many natural language processing tasks. Despite rigorous safety alignment processes, supposedly safety-aligned LLMs like Llama 2 and Claude 2 are still susceptible to jailbreaks, leading to…

Computation and Language · Computer Science 2024-05-15 Ziyang Zhang , Qizhen Zhang , Jakob Foerster

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

As large language models (LLMs) become increasingly integrated into daily applications, it is essential to ensure they operate fairly across diverse user demographics. In this work, we show that LLMs suffer from personalization bias, where…

Computation and Language · Computer Science 2025-02-12 Anvesh Rao Vijjini , Somnath Basu Roy Chowdhury , Snigdha Chaturvedi

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with…

Cryptography and Security · Computer Science 2026-01-21 Zhixin Xie , Xurui Song , Jun Luo

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Cryptography and Security · Computer Science 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Artificial Intelligence · Computer Science 2026-04-03 Hamin Koo , Minseon Kim , Jaehyung Kim

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability…

Artificial Intelligence · Computer Science 2026-04-15 Wenkai Li , Fan Yang , Shaunak A. Mehta , Koichi Onoue

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Cryptography and Security · Computer Science 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model…

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Cryptography and Security · Computer Science 2025-02-24 Pedram Zaree , Md Abdullah Al Mamun , Quazi Mishkatul Alam , Yue Dong , Ihsen Alouani , Nael Abu-Ghazaleh

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi
‹ Prev 1 3 4 5 6 7 10 Next ›