English
Related papers

Related papers: Jailbreak Transferability Emerges from Shared Repr…

200 papers

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Cryptography and Security · Computer Science 2026-05-12 Yu Chen , Yuanhao Liu , Qi Cao

Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…

Machine Learning · Computer Science 2026-02-06 Licheng Pan , Yunsheng Lu , Jiexi Liu , Jialing Tao , Haozhe Feng , Hui Xue , Zhixuan Chu , Kui Ren

Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…

Machine Learning · Computer Science 2021-07-16 Ramesh Kumar Sah , Hassan Ghasemzadeh

One intriguing property of adversarial attacks is their "transferability" -- an adversarial example crafted with respect to one deep neural network (DNN) model is often found effective against other DNNs as well. Intensive research has been…

Computer Vision and Pattern Recognition · Computer Science 2022-04-11 Yuhao Mao , Chong Fu , Saizhuo Wang , Shouling Ji , Xuhong Zhang , Zhenguang Liu , Jun Zhou , Alex X. Liu , Raheem Beyah , Ting Wang

Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…

Machine Learning · Computer Science 2020-10-28 Seng Pei Liew , Tsubasa Takahashi

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK…

Cryptography and Security · Computer Science 2026-03-06 Zhicheng Fang , Jingjie Zheng , Chenxu Fu , Wei Xu

Transfer learning has become a common solution to address training data scarcity in practice. It trains a specified student model by reusing or fine-tuning early layers of a well-trained teacher model that is usually publicly available.…

Cryptography and Security · Computer Science 2022-06-24 Yufei Chen , Chao Shen , Cong Wang , Yang Zhang

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

Cryptography and Security · Computer Science 2025-12-18 Yixin Tan , Zhe Yu , Jun Sakuma

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

Cryptography and Security · Computer Science 2025-05-21 Zhexin Zhang , Junxiao Yang , Yida Lu , Pei Ke , Shiyao Cui , Chujie Zheng , Hongning Wang , Minlie Huang

Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand…

Machine Learning · Computer Science 2021-07-12 Kaizhao Liang , Jacky Y. Zhang , Boxin Wang , Zhuolin Yang , Oluwasanmi Koyejo , Bo Li

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo

Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern. A major issue is that these models are susceptible to adversarial attacks, where small,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Jie Ning , Jiebao Sun , Shengzhu Shi , Zhichang Guo , Yao Li , Hongwei Li , Boying Wu

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Further, these adversarial examples are found to be transferable from the source network in which they are crafted to a black-box target network. As the trend…

Machine Learning · Computer Science 2024-05-17 Abhishek Shrestha , Jürgen Großmann

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Computation and Language · Computer Science 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…

Computation and Language · Computer Science 2026-04-29 Shirin Alanova , Bogdan Minko , Sabrina Sadiekh , Evgeniy Kokuykin

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…

Cryptography and Security · Computer Science 2024-09-02 Sibo Yi , Yule Liu , Zhen Sun , Tianshuo Cong , Xinlei He , Jiaxing Song , Ke Xu , Qi Li

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little…

Machine Learning · Computer Science 2025-09-30 Zeyu Michael Li , Hung Anh Vu , Damilola Awofisayo , Emily Wenger

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yao Zhu , Yuefeng Chen , Xiaodan Li , Kejiang Chen , Yuan He , Xiang Tian , Bolun Zheng , Yaowu Chen , Qingming Huang