English
Related papers

Related papers: Stealix: Model Stealing via Prompt Evolution

200 papers

Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily…

Cryptography and Security · Computer Science 2024-12-18 Shubhi Shukla , Manaar Alam , Pabitra Mitra , Debdeep Mukhopadhyay

We investigate whether model extraction can be used to "steal" the weights of sequential recommender systems, and the potential threats posed to victims of such attacks. This type of risk has attracted attention in image and text…

Cryptography and Security · Computer Science 2021-09-06 Zhenrui Yue , Zhankui He , Huimin Zeng , Julian McAuley

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Machine Learning · Computer Science 2024-11-05 Shengchao Hu , Wanru Zhao , Weixiong Lin , Li Shen , Ya Zhang , Dacheng Tao

Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly similar samples. When such samples are…

Cryptography and Security · Computer Science 2026-02-02 Farnaz Soltaniani , Mohammad Ghafari

Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness. Existing fairness techniques that address label bias…

Machine Learning · Computer Science 2024-12-17 Yixuan Zhang , Zhidong Li , Yang Wang , Fang Chen , Xuhui Fan , Feng Zhou

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…

Robotics · Computer Science 2025-10-28 Amirreza Razmjoo , Sylvain Calinon , Michael Gienger , Fan Zhang

Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the…

Machine Learning · Computer Science 2025-12-09 S. M. Mustaqim , Anantaa Kotal , Paul H. Yi

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Shivam Chandhok , Qian Yang , Oscar Manas , Kanishk Jain , Leonid Sigal , Aishwarya Agrawal

Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicious customers to conduct model extraction attacks, i.e.,…

Cryptography and Security · Computer Science 2023-06-14 Shiqian Zhao , Kangjie Chen , Meng Hao , Jian Zhang , Guowen Xu , Hongwei Li , Tianwei Zhang

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

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

Machine Learning · Computer Science 2026-04-21 Anna Mazhar , Sainyam Galhotra

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…

Computation and Language · Computer Science 2023-11-10 Luca Beurer-Kellner , Mark Niklas Müller , Marc Fischer , Martin Vechev

Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering content via text prompts. However, many undesired outputs, such as…

Machine Learning · Computer Science 2026-03-13 Kyungryeol Lee , Kyeonghyun Lee , Seongmin Hong , Byung Hyun Lee , Se Young Chun

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Cryptography and Security · Computer Science 2018-11-02 Luca Melis , Congzheng Song , Emiliano De Cristofaro , Vitaly Shmatikov

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…

Cryptography and Security · Computer Science 2025-06-24 Yash Sinha , Manit Baser , Murari Mandal , Dinil Mon Divakaran , Mohan Kankanhalli

Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained proprietarily, where neither pre-trained models nor sufficient…

Machine Learning · Computer Science 2021-04-14 Xinyi Zhang , Chengfang Fang , Jie Shi

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…

Cryptography and Security · Computer Science 2022-11-01 Xuanli He , Chen Chen , Lingjuan Lyu , Qiongkai Xu

In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Jaeseok Jeong , Junho Kim , Yunjey Choi , Gayoung Lee , Youngjung Uh

Large pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to the privacy risk of…

Computation and Language · Computer Science 2023-07-11 Zhexin Zhang , Jiaxin Wen , Minlie Huang