English
Related papers

Related papers: GradShield: Alignment Preserving Finetuning

200 papers

Large Language Models (LLMs) have shown impressive proficiency in code generation. Unfortunately, these models share a weakness with their human counterparts: producing code that inadvertently has security vulnerabilities. These…

Cryptography and Security · Computer Science 2024-10-17 Kamel Alrashedy , Abdullah Aljasser , Pradyumna Tambwekar , Matthew Gombolay

Federated Learning (FL) has recently emerged as a revolutionary approach to collaborative training Machine Learning models. In particular, it enables decentralized model training while preserving data privacy, but its distributed nature…

Cryptography and Security · Computer Science 2025-12-30 Sameera K. M. , Serena Nicolazzo , Antonino Nocera , Vinod P. , Rafidha Rehiman K. A

Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…

Computation and Language · Computer Science 2024-06-13 Bochuan Cao , Yuanpu Cao , Lu Lin , Jinghui Chen

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Computation and Language · Computer Science 2022-10-20 Chenghao Yang , Xuezhe Ma

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Cryptography and Security · Computer Science 2026-04-28 Zihan Liu , Yizhen Wang , Rui Wang , Xiu Tang , Sai Wu

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Artificial Intelligence · Computer Science 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

Artificial Intelligence · Computer Science 2025-10-24 Wonje Jeung , Sangyeon Yoon , Minsuk Kahng , Albert No

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

Cryptography and Security · Computer Science 2026-05-01 Mahshid Rezakhani , Nowfel Mashnoor , Kimia Azar , Hadi Kamali

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Machine Learning · Computer Science 2025-07-08 Jeremiah Giordani

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…

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…

Artificial Intelligence · Computer Science 2025-01-17 Huandong Wang , Wenjie Fu , Yingzhou Tang , Zhilong Chen , Yuxi Huang , Jinghua Piao , Chen Gao , Fengli Xu , Tao Jiang , Yong Li

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Machine Learning · Computer Science 2026-02-13 Zhaoxin Wang , Jiaming Liang , Fengbin Zhu , Weixiang Zhao , Junfeng Fang , Jiayi Ji , Handing Wang , Tat-Seng Chua

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Computation and Language · Computer Science 2024-08-06 Yuxia Wang , Zenan Zhai , Haonan Li , Xudong Han , Lizhi Lin , Zhenxuan Zhang , Jingru Zhao , Preslav Nakov , Timothy Baldwin

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

Machine Learning · Computer Science 2025-09-30 Javad Forough , Mohammad Maheri , Hamed Haddadi

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…

Artificial Intelligence · Computer Science 2023-07-25 David Glukhov , Ilia Shumailov , Yarin Gal , Nicolas Papernot , Vardan Papyan

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Cryptography and Security · Computer Science 2025-08-15 Jinhwa Kim , Ian G. Harris

This paper investigates supervised fine-tuning of large language models (LLMs) to improve their pedagogical alignment in computing education, addressing concerns that LLMs may hinder learning outcomes. The project utilised a proprietary…

Computation and Language · Computer Science 2024-11-05 Alexandra Vassar , Jake Renzella , Emily Ross , Andrew Taylor

The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values. This requirement challenges existing alignment methods due to diversity of preferences and regulatory standards. This paper…

Computation and Language · Computer Science 2024-02-28 Xinyu Lu , Bowen Yu , Yaojie Lu , Hongyu Lin , Haiyang Yu , Le Sun , Xianpei Han , Yongbin Li

The rapid adoption of open-source Large Language Models (LLMs) in offline and enterprise environments has introduced a largely unexamined security risk like susceptibility to adversarial phishing prompts under static safety configurations.…

Cryptography and Security · Computer Science 2026-04-21 Rina Mishra , Gaurav Varshney , Doddipatla Sesha Sahithi