English
Related papers

Related papers: GradShield: Alignment Preserving Finetuning

200 papers

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

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are…

Cryptography and Security · Computer Science 2024-12-11 Xiangyu Qi , Boyi Wei , Nicholas Carlini , Yangsibo Huang , Tinghao Xie , Luxi He , Matthew Jagielski , Milad Nasr , Prateek Mittal , Peter Henderson

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

Cryptography and Security · Computer Science 2026-03-24 Marco Arazzi , Vignesh Kumar Kembu , Antonino Nocera

Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations of…

Computation and Language · Computer Science 2024-06-12 Pratiksha Thaker , Yash Maurya , Shengyuan Hu , Zhiwei Steven Wu , Virginia Smith

Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various…

Cryptography and Security · Computer Science 2025-04-22 Jiangnan Li , Yingyuan Yang , Jinyuan Sun

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Cryptography and Security · Computer Science 2025-06-13 Kaiyuan Zhang , Siyuan Cheng , Hanxi Guo , Yuetian Chen , Zian Su , Shengwei An , Yuntao Du , Charles Fleming , Ashish Kundu , Xiangyu Zhang , Ninghui Li

Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a…

Software Engineering · Computer Science 2024-09-17 Mingke Yang , Yuqi Chen , Yi Liu , Ling Shi

Why is safety alignment in LLMs shallow? We prove that gradient-based alignment inherently concentrates on positions where harm is decided and vanishes beyond. Using a martingale decomposition of sequence-level harm, we derive an exact…

Machine Learning · Computer Science 2026-03-06 Robin Young

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly…

Cryptography and Security · Computer Science 2025-08-28 Chao Huang , Zefeng Zhang , Juewei Yue , Quangang Li , Chuang Zhang , Tingwen Liu

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for…

Software Engineering · Computer Science 2024-07-26 Hongwei Jin , George Papadimitriou , Krishnan Raghavan , Pawel Zuk , Prasanna Balaprakash , Cong Wang , Anirban Mandal , Ewa Deelman

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

Computation and Language · Computer Science 2024-03-01 Jiabao Ji , Bairu Hou , Alexander Robey , George J. Pappas , Hamed Hassani , Yang Zhang , Eric Wong , Shiyu Chang

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models…

Computation and Language · Computer Science 2025-02-25 Seanie Lee , Haebin Seong , Dong Bok Lee , Minki Kang , Xiaoyin Chen , Dominik Wagner , Yoshua Bengio , Juho Lee , Sung Ju Hwang

Large Language Models (LLMs) represent an advanced evolution of earlier, simpler language models. They boast enhanced abilities to handle complex language patterns and generate coherent text, images, audios, and videos. Furthermore, they…

Cryptography and Security · Computer Science 2024-03-01 Jun Huang , Jiawei Zhang , Qi Wang , Weihong Han , Yanchun Zhang

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine

Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human intervention. While attackers take advantage of dark LLMs such as XXXGPT and WolfGPT to produce…

Cryptography and Security · Computer Science 2026-04-14 Ricardo Bessa , Rui Claro , João Trindade , João Lourenço

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…

Cryptography and Security · Computer Science 2024-06-21 Suriya Ganesh Ayyamperumal , Limin Ge

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) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

Computation and Language · Computer Science 2025-08-21 Badrinath Ramakrishnan , Akshaya Balaji
‹ Prev 1 8 9 10 Next ›