English
Related papers

Related papers: Superficial Safety Alignment Hypothesis

200 papers

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety…

Artificial Intelligence · Computer Science 2025-07-22 Yi Zhang , An Zhang , XiuYu Zhang , Leheng Sheng , Yuxin Chen , Zhenkai Liang , Xiang Wang

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Cryptography and Security · Computer Science 2026-04-06 John T. Halloran

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing…

Cryptography and Security · Computer Science 2026-03-16 Jinman Wu , Yi Xie , Shiqian Zhao , Xiaofeng Chen

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world…

Machine Learning · Computer Science 2026-04-21 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical…

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

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

Computation and Language · Computer Science 2024-06-14 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Yongbin Li

Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted prompts bypass safety mechanisms. Understanding the causal factors behind such…

Cryptography and Security · Computer Science 2025-12-05 Wei Zhao , Zhe Li , Jun Sun

User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this work, drawing inspiration from such access control systems,…

Computation and Language · Computer Science 2025-12-04 Soumadeep Saha , Akshay Chaturvedi , Joy Mahapatra , Utpal Garain

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Cryptography and Security · Computer Science 2025-05-27 Haoyu Wang , Zeyu Qin , Yifei Zhao , Chao Du , Min Lin , Xueqian Wang , Tianyu Pang

As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) will become essential due to their efficiency in reducing computation…

Machine Learning · Computer Science 2025-01-06 Mingjie Li , Wai Man Si , Michael Backes , Yang Zhang , Yisen Wang

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by…

Machine Learning · Computer Science 2024-10-30 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Ling Liu

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

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Artificial Intelligence · Computer Science 2025-09-17 Wei Cai , Shujuan Liu , Jian Zhao , Ziyan Shi , Yusheng Zhao , Yuchen Yuan , Tianle Zhang , Chi Zhang , Xuelong Li

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

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

Automating hardware (HW) security vulnerability detection and mitigation during the design phase is imperative for two reasons: (i) It must be before chip fabrication, as post-fabrication fixes can be costly or even impractical; (ii) The…

Cryptography and Security · Computer Science 2024-04-26 Mohammad Akyash , Hadi Mardani Kamali

Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies for safety intervention across diverse tasks. To better…

Cryptography and Security · Computer Science 2026-04-10 Weiwei Qi , Zefeng Wu , Tianhang Zheng , Zikang Zhang , Xiaojun Jia , Zhan Qin , Kui Ren

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Computation and Language · Computer Science 2024-10-29 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria