English
Related papers

Related papers: Consistent but Dangerous: Per-Sample Safety Classi…

200 papers

Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safety mechanism for text…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Shicheng Xu , Liang Pang , Yunchang Zhu , Huawei Shen , Xueqi Cheng

We consider a class of semiparametric regression models which are one-parameter extensions of the Cox [J. Roy. Statist. Soc. Ser. B 34 (1972) 187-220] model for right-censored univariate failure times. These models assume that the hazard…

Statistics Theory · Mathematics 2007-06-13 Michael R. Kosorok , Bee Leng Lee , Jason P. Fine

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…

Cryptography and Security · Computer Science 2026-05-19 Isaac David , Arthur Gervais

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Artificial Intelligence · Computer Science 2025-06-27 Chenkai Sun , Denghui Zhang , ChengXiang Zhai , Heng Ji

As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English to other languages remains a dangerous blind spot. This study presents a systematic audit…

Computation and Language · Computer Science 2026-01-09 Muhammad Abdullahi Said , Muhammad Sammani Sani

Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…

Machine Learning · Computer Science 2026-02-03 Prakhar Ganesh , Reza Shokri , Golnoosh Farnadi

Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods…

Machine Learning · Computer Science 2026-02-23 Zongmin Li , Jian Su , Farah Benamara , Aixin Sun

Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible but factually incorrect findings that pose direct patient safety risks. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Haoyu Wang , Zitong Li

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

Computation and Language · Computer Science 2026-05-21 Mengya Hu , Qiong Wei , Sandeep Atluri

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Computation and Language · Computer Science 2025-10-15 Trishna Chakraborty , Erfan Shayegani , Zikui Cai , Nael Abu-Ghazaleh , M. Salman Asif , Yue Dong , Amit K. Roy-Chowdhury , Chengyu Song

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…

Computation and Language · Computer Science 2024-08-30 Ruchira Ray , Ruchi Bhalani

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

Machine Learning · Computer Science 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Machine Learning · Computer Science 2025-01-29 Qing Li , Jiahui Geng , Zongxiong Chen , Kun Song , Lei Ma , Fakhri Karray

Machine learning (ML) models show strong promise for new biomedical prediction tasks, but concerns about trustworthiness have hindered their clinical adoption. In particular, it is often unclear whether a model relies on true clinical cues…

Machine Learning · Computer Science 2026-01-13 Dushan N. Wadduwage , Dineth Jayakody , Leonidas Zimianitis

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false…

Machine Learning · Computer Science 2026-03-17 Quan Liu , Han Zhou , Wenquan Wu , Hua Wu , Sen Su

Large Language Models (LLMs) are increasingly used for medical entity extraction, yet their confidence scores are often miscalibrated, limiting safe deployment in clinical settings. We present a conformal prediction framework that provides…

Computation and Language · Computer Science 2026-03-10 Manil Shrestha , Edward Kim

Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment. However, existing benchmarks suffer from three fundamental limitations: (1) heavy reliance on synthetic datasets…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Qiucheng Yu , Ruijie Xu , Mingang Chen , Xuequan Lu , Jianfeng Dong , Chaochao Lu , Xin Tan

The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while…

Information Retrieval · Computer Science 2025-05-28 Jiahui Geng , Qing Li , Zongxiong Chen , Yuxia Wang , Derui Zhu , Zhuohan Xie , Chenyang Lyu , Xiuying Chen , Preslav Nakov , Fakhri Karray

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic…

Machine Learning · Computer Science 2026-04-24 Junxiao Yang , Haoran Liu , Jinzhe Tu , Jiale Cheng , Zhexin Zhang , Shiyao Cui , Jiaqi Weng , Jialing Tao , Hui Xue , Hongning Wang , Han Qiu , Minlie Huang