English
Related papers

Related papers: Safety Alignment via Constrained Knowledge Unlearn…

200 papers

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Shuang Liang , Zhihao Xu , Jialing Tao , Hui Xue , Xiting Wang

Federated Learning (FL) offers a promising paradigm for training Large Language Models (LLMs) in a decentralized manner while preserving data privacy and minimizing communication overhead. This survey examines recent advancements in…

Machine Learning · Computer Science 2025-05-12 Youyang Qu , Ming Liu , Tianqing Zhu , Longxiang Gao , Shui Yu , Wanlei Zhou

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

Cryptography and Security · Computer Science 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Machine Learning · Computer Science 2026-02-02 Hsiang Hsu , Pradeep Niroula , Zichang He , Ivan Brugere , Freddy Lecue , Chun-Fu Chen

Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes…

Machine Learning · Computer Science 2025-05-15 Timothy Qian , Vinith Suriyakumar , Ashia Wilson , Dylan Hadfield-Menell

Large language models (LLMs) have demonstrated remarkable capabilities, but they also pose risks related to the generation of toxic or harmful content. This work introduces Precision Knowledge Editing (PKE), an advanced technique that…

Computation and Language · Computer Science 2024-10-14 Xuying Li , Zhuo Li , Yuji Kosuga , Yasuhiro Yoshida , Victor Bian

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Large Language and Vision-Language Models (LLMs/VLMs) are increasingly used in safety-critical applications, yet their opaque decision-making complicates risk assessment and reliability. Uncertainty quantification (UQ) helps assess…

Machine Learning · Computer Science 2025-02-12 Sina Tayebati , Divake Kumar , Nastaran Darabi , Dinithi Jayasuriya , Ranganath Krishnan , Amit Ranjan Trivedi

As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting,…

Machine Learning · Computer Science 2025-09-19 Jiaxing Miao , Liang Hu , Qi Zhang , Lai Zhong Yuan , Usman Naseem

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

Deep learning (DL) enabled semantic communications leverage DL to train encoders and decoders (codecs) to extract and recover semantic information. However, most semantic training datasets contain personal private information. Such concerns…

Cryptography and Security · Computer Science 2025-02-28 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Shui Yu

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for…

Machine Learning · Computer Science 2025-06-23 Wenhan Chang , Tianqing Zhu , Ping Xiong , Yufeng Wu , Faqian Guan , Wanlei Zhou

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Computation and Language · Computer Science 2024-10-15 Minjun Zhu , Linyi Yang , Yifan Wei , Ningyu Zhang , Yue Zhang

Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging: intermediate chain-of-thought steps can still leak sensitive…

Computation and Language · Computer Science 2025-12-23 Hongji Li , Junchi yao , Manjiang Yu , Priyanka Singh , Xue Li , Di Wang , Lijie Hu

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

Software Engineering · Computer Science 2025-09-18 Zhaoyang Chu , Yao Wan , Zhikun Zhang , Di Wang , Zhou Yang , Hongyu Zhang , Pan Zhou , Xuanhua Shi , Hai Jin , David Lo

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

Machine Learning · Computer Science 2025-11-04 Myeongseob Ko , Hoang Anh Just , Charles Fleming , Ming Jin , Ruoxi Jia

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

Recent progress in Machine Unlearning (MU) has introduced solutions for the selective removal of private or sensitive information encoded within deep neural networks. Nonetheless, MU for Multimodal Large Language Models (MLLMs) remains in…

Computation and Language · Computer Science 2025-05-28 Jiahao Huo , Yibo Yan , Xu Zheng , Yuanhuiyi Lyu , Xin Zou , Zhihua Wei , Xuming Hu

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…