English
Related papers

Related papers: BadMerging: Backdoor Attacks Against Model Merging

200 papers

Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning…

Machine Learning · Computer Science 2020-07-08 Yang Liu , Zhihao Yi , Tianjian Chen

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Cryptography and Security · Computer Science 2024-04-02 Shanglun Feng , Florian Tramèr

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform abnormal actions leading to failures or malicious…

Artificial Intelligence · Computer Science 2024-09-13 Yinbo Yu , Saihao Yan , Jiajia Liu

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the…

Machine Learning · Computer Science 2025-09-03 Zihao Wang , Enneng Yang , Lu Yin , Shiwei Liu , Li Shen

Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and…

Cryptography and Security · Computer Science 2024-08-23 Jiang Hao , Xiao Jin , Hu Xiaoguang , Chen Tianyou , Zhao Jiajia

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…

Machine Learning · Computer Science 2023-08-08 Hang Wang , Zhen Xiang , David J. Miller , George Kesidis

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Machine Learning · Computer Science 2026-02-09 Haiyun Qiu , Xingyu Wu , Liang Feng , Kay Chen Tan

The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main…

Machine Learning · Computer Science 2024-12-03 Jiakai Wang , Pengfei Zhang , Renshuai Tao , Jian Yang , Hao Liu , Xianglong Liu , Yunchao Wei , Yao Zhao

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Machine Learning · Computer Science 2023-10-30 Prateek Yadav , Derek Tam , Leshem Choshen , Colin Raffel , Mohit Bansal

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the…

Cryptography and Security · Computer Science 2024-01-24 Zhen Xiang , Fengqing Jiang , Zidi Xiong , Bhaskar Ramasubramanian , Radha Poovendran , Bo Li

Visual State Space Models (VSSM) have shown remarkable performance in various computer vision tasks. However, backdoor attacks pose significant security challenges, causing compromised models to predict target labels when specific triggers…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Cheng-Yi Lee , Yu-Hsuan Chiang , Zhong-You Wu , Chia-Mu Yu , Chun-Shien Lu

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Machine Learning · Computer Science 2024-03-12 Xiaoyang Wang , Dimitrios Dimitriadis , Sanmi Koyejo , Shruti Tople

As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor…

Machine Learning · Computer Science 2021-10-12 Siddhartha Datta , Giulio Lovisotto , Ivan Martinovic , Nigel Shadbolt

Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their…

Cryptography and Security · Computer Science 2025-11-25 Jiayi Luo , Qingyun Sun , Lingjuan Lyu , Ziwei Zhang , Haonan Yuan , Xingcheng Fu , Jianxin Li

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on…

Cryptography and Security · Computer Science 2019-03-13 Tianyu Gu , Brendan Dolan-Gavitt , Siddharth Garg

Federated learning (FL) is a decentralized machine learning technique that allows multiple entities to jointly train a model while preserving dataset privacy. However, its distributed nature has raised various security concerns, which have…

Cryptography and Security · Computer Science 2025-01-06 Nuno Neves

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Cryptography and Security · Computer Science 2021-02-22 Eugene Bagdasaryan , Vitaly Shmatikov

Foundation model has become the backbone of the AI ecosystem. In particular, a foundation model can be used as a general-purpose feature extractor to build various downstream classifiers. However, foundation models are vulnerable to…

Cryptography and Security · Computer Science 2024-02-26 Hongbin Liu , Michael K. Reiter , Neil Zhenqiang Gong

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang
‹ Prev 1 4 5 6 7 8 10 Next ›