English
Related papers

Related papers: Surgery: Mitigating Harmful Fine-Tuning for Large …

200 papers

Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Computation and Language · Computer Science 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs…

Computation and Language · Computer Science 2026-03-10 Le Yu , Zhengyue Zhao , Yawen Zheng , Yunhao Liu

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data…

Computation and Language · Computer Science 2021-04-13 Xisen Jin , Francesco Barbieri , Brendan Kennedy , Aida Mostafazadeh Davani , Leonardo Neves , Xiang Ren

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel framework that leverages adaptive noise injection based on…

Computation and Language · Computer Science 2025-05-06 Afshin Khadangi , Amir Sartipi , Igor Tchappi , Ramin Bahmani

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Computation and Language · Computer Science 2026-04-21 Zhexin Zhang , Xian Qi Loye , Victor Shea-Jay Huang , Junxiao Yang , Qi Zhu , Shiyao Cui , Fei Mi , Lifeng Shang , Yingkang Wang , Hongning Wang , Minlie Huang

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Computation and Language · Computer Science 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Machine Learning · Computer Science 2026-05-13 Guanglong Sun , Siyuan Zhang , Liyuan Wang , Jun Zhu , Hang Su , Yi Zhong

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Computation and Language · Computer Science 2026-03-05 Yuxiao Lu , Lin Xu , Yang Sun , Wenjun Li , Jie Shi

In convolutional neural network based medical image segmentation, the periphery of foreground regions representing malignant tissues may be disproportionately assigned as belonging to the background class of healthy tissues…

Computer Vision and Pattern Recognition · Computer Science 2020-08-10 Mou-Cheng Xu , Neil P. Oxtoby , Daniel C. Alexander , Joseph Jacob

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Cryptography and Security · Computer Science 2026-01-26 Xianya Fang , Xianying Luo , Yadong Wang , Xiang Chen , Yu Tian , Zequn Sun , Rui Liu , Jun Fang , Naiqiang Tan , Yuanning Cui , Sheng-Jun Huang

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

Computation and Language · Computer Science 2023-08-29 Charles O'Neill , Jack Miller , Ioana Ciuca , Yuan-Sen Ting , Thang Bui

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Despite the rapid progress in self-supervised learning (SSL), end-to-end fine-tuning still remains the dominant fine-tuning strategy for medical imaging analysis. However, it remains unclear whether this approach is truly optimal for…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Muhammad Osama Khan , Yi Fang

Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards and induces unsafe behaviors. We propose SPARD, a defense…

Machine Learning · Computer Science 2026-05-28 Shuhao Chen , Weisen Jiang , Yeqi Gong , Shengda Luo , Chengxiang Zhuo , Zang Li , James T. Kwok , Yu Zhang