English
Related papers

Related papers: Fine-tuning Aligned Language Models Compromises Sa…

200 papers

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

Cryptography and Security · Computer Science 2025-12-25 Zhengchun Shang , Wenlan Wei , Weiheng Bai

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

Artificial Intelligence · Computer Science 2024-12-25 Dan Shi , Tianhao Shen , Yufei Huang , Zhigen Li , Yongqi Leng , Renren Jin , Chuang Liu , Xinwei Wu , Zishan Guo , Linhao Yu , Ling Shi , Bojian Jiang , Deyi Xiong

As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse…

Machine Learning · Computer Science 2025-06-03 Saad Hossain , Samanvay Vajpayee , Sirisha Rambhatla

Large language model (LLM) providers often hide the architectural details and parameters of their proprietary models by restricting public access to a limited API. In this work we show that, with only a conservative assumption about the…

Computation and Language · Computer Science 2024-11-11 Matthew Finlayson , Xiang Ren , Swabha Swayamdipta

In this work, we designed unbiased prompts to systematically evaluate the psychological safety of large language models (LLMs). First, we tested five different LLMs by using two personality tests: Short Dark Triad (SD-3) and Big Five…

Computation and Language · Computer Science 2024-03-01 Xingxuan Li , Yutong Li , Lin Qiu , Shafiq Joty , Lidong Bing

Large Language Models (LLMs) are powerful tools for natural language processing, enabling novel applications and user experiences. However, to achieve optimal performance, LLMs often require adaptation with private data, which poses privacy…

Cryptography and Security · Computer Science 2023-10-18 Rui Wen , Tianhao Wang , Michael Backes , Yang Zhang , Ahmed Salem

Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's difficulty by how often the target model's own rollouts are judged harmful, then fine-tune…

Machine Learning · Computer Science 2026-05-06 Prakhar Gupta , Garv Shah , Donghua Zhang

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Computation and Language · Computer Science 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Computation and Language · Computer Science 2024-01-25 Lingfeng Shen , Weiting Tan , Sihao Chen , Yunmo Chen , Jingyu Zhang , Haoran Xu , Boyuan Zheng , Philipp Koehn , Daniel Khashabi

As large language models (LLMs) become increasingly integrated into real-world applications, scalable and rigorous safety evaluation is essential. This paper introduces Aymara AI, a programmatic platform for generating and administering…

Artificial Intelligence · Computer Science 2026-05-01 Juan Manuel Contreras

Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the…

Software Engineering · Computer Science 2025-01-30 Aitor Arrieta , Miriam Ugarte , Pablo Valle , José Antonio Parejo , Sergio Segura

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize…

Computation and Language · Computer Science 2024-05-16 Xin Yi , Shunfan Zheng , Linlin Wang , Xiaoling Wang , Liang He

We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…

Artificial Intelligence · Computer Science 2026-02-10 Soumi Das , Camila Kolling , Mohammad Aflah Khan , Mahsa Amani , Bishwamittra Ghosh , Qinyuan Wu , Till Speicher , Krishna P. Gummadi

Recent advancements in large language models (LLMs) have significantly enhanced capabilities in natural language processing and artificial intelligence. These models, including GPT-3.5 and LLaMA-2, have revolutionized text generation,…

Computation and Language · Computer Science 2024-02-06 Yunhong He , Jianling Qiu , Wei Zhang , Zhengqing Yuan

The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…

Computation and Language · Computer Science 2024-12-18 Xin Yi , Shunfan Zheng , Linlin Wang , Gerard de Melo , Xiaoling Wang , Liang He

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Truyen Tran

Recent advancements in Large Language Models (LLMs), such as ChatGPT and LLaMA, have significantly transformed Natural Language Processing (NLP) with their outstanding abilities in text generation, summarization, and classification.…

Computation and Language · Computer Science 2024-08-12 Md Nazmus Sakib , Md Athikul Islam , Royal Pathak , Md Mashrur Arifin

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Machine Learning · Computer Science 2024-02-28 Heegyu Kim , Sehyun Yuk , Hyunsouk Cho

Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechanism in which harmful inputs are routed safety-critical…

Cryptography and Security · Computer Science 2025-10-10 Jaehan Kim , Minkyoo Song , Seungwon Shin , Sooel Son