中文
相关论文

相关论文: Benign Samples Matter! Fine-tuning On Outlier Beni…

200 篇论文

The rapid evolution of malware variants requires robust classification methods to enhance cybersecurity. While Large Language Models (LLMs) offer potential for generating malware descriptions to aid family classification, their utility is…

密码学与安全 · 计算机科学 2025-05-01 Ivan Montoya Sanchez , Shaswata Mitra , Aritran Piplai , Sudip Mittal

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

密码学与安全 · 计算机科学 2026-01-13 Shawn Li , Chenxiao Yu , Zhiyu Ni , Hao Li , Charith Peris , Chaowei Xiao , Yue Zhao

The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general…

计算与语言 · 计算机科学 2023-04-19 Da Silva Gameiro Henrique , Andrei Kucharavy , Rachid Guerraoui

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

密码学与安全 · 计算机科学 2025-06-02 Jianwei Li , Jung-Eun Kim

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…

计算与语言 · 计算机科学 2025-10-29 Marton Szep , Daniel Rueckert , Rüdiger von Eisenhart-Rothe , Florian Hinterwimmer

Unit testing plays a pivotal role in software development, improving software quality and reliability. However, generating effective test cases manually is time-consuming, prompting interest in unit testing research. Recently, Large…

软件工程 · 计算机科学 2024-12-24 Ye Shang , Quanjun Zhang , Chunrong Fang , Siqi Gu , Jianyi Zhou , Zhenyu Chen

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

计算与语言 · 计算机科学 2024-06-25 Simone Tedeschi , Felix Friedrich , Patrick Schramowski , Kristian Kersting , Roberto Navigli , Huu Nguyen , Bo Li

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models (LLMs) have emerged as a promising tool for automated security tasks, their…

密码学与安全 · 计算机科学 2026-03-03 Ahmed Ryan , Ibrahim Khalil , Abdullah Al Jahid , Md Erfan , Sungbin Park , Akond Ashfaque Ur Rahman , Md Rayhanur Rahman

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scaling properties) of different finetuning methods is still…

计算与语言 · 计算机科学 2024-02-28 Biao Zhang , Zhongtao Liu , Colin Cherry , Orhan Firat

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

计算与语言 · 计算机科学 2025-10-06 Zhe Li , Wei Zhao , Yige Li , Jun Sun

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

计算与语言 · 计算机科学 2026-03-10 Guoli Wang , Haonan Shi , Tu Ouyang , An Wang

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

机器学习 · 计算机科学 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

Background: Leaking sensitive information - such as API keys, tokens, and credentials - in source code remains a persistent security threat. Traditional regex and entropy-based tools often generate high false positives due to limited…

软件工程 · 计算机科学 2025-07-29 Md Nafiu Rahman , Sadif Ahmed , Zahin Wahab , S M Sohan , Rifat Shahriyar

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

计算与语言 · 计算机科学 2024-10-18 Shuyang Jiang , Yusheng Liao , Ya Zhang , Yanfeng Wang , Yu Wang

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

计算与语言 · 计算机科学 2024-09-04 Myung Gyo Oh , Hong Eun Ahn , Leo Hyun Park , Taekyoung Kwon

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

计算与语言 · 计算机科学 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

密码学与安全 · 计算机科学 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

计算与语言 · 计算机科学 2025-12-12 Lama Alssum , Hani Itani , Hasan Abed Al Kader Hammoud , Philip Torr , Adel Bibi , Bernard Ghanem