English
Related papers

Related papers: Poison Once, Refuse Forever: Weaponizing Alignment…

200 papers

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for…

Computation and Language · Computer Science 2024-09-26 Samuel Pfrommer , Yatong Bai , Tanmay Gautam , Somayeh Sojoudi

The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic…

Cryptography and Security · Computer Science 2026-05-19 Yanyun Wang , Yu Huang , Zi Liang , Xixin Wu , Li Liu

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies on human annotators…

Artificial Intelligence · Computer Science 2024-06-21 Jiongxiao Wang , Junlin Wu , Muhao Chen , Yevgeniy Vorobeychik , Chaowei Xiao

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Machine Learning · Computer Science 2026-03-03 Yuhui Wang , Rongyi Zhu , Ting Wang

The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in \textit{primum non nocere}. However, current alignment techniques rely on generic definitions of harm that fail to capture context-dependent…

Computers and Society · Computer Science 2025-12-01 Andrew Maranhão Ventura D'addario

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Cryptography and Security · Computer Science 2026-04-02 Anubhab Sahu , Diptisha Samanta , Reza Soosahabi

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Cryptography and Security · Computer Science 2025-11-26 Benji Peng , Keyu Chen , Ming Li , Pohsun Feng , Ziqian Bi , Junyu Liu , Xinyuan Song , Qian Niu

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

Cryptography and Security · Computer Science 2024-06-18 Stephen Burabari Tete

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the robustness of these models against subtle linguistic variations, specifically…

Computation and Language · Computer Science 2026-05-19 Jen-tse Huang , Didi Zhou , Faith Kamau , Amy Oh , Anne R. Links , Mark Dredze , Mary Catherine Beach , Somnath Saha

Large Vision-Language Models (LVLMs) suffer from serious hallucination problems, where the model-generated responses are inconsistent with the visual inputs. Existing hallucination mitigation methods are mainly based on preference alignment…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Yifan Lu , Ziqi Zhang , Chunfeng Yuan , Jun Gao , Congxuan Zhang , Xiaojuan Qi , Bing Li , Weiming Hu

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…

Cryptography and Security · Computer Science 2026-05-12 Yulong Chen , Qi Zhang , Jiawen Zhang , Yadong Liu , Mu Li , Jie Wen , Yong Xu

Advances in large language models (LLMs) have driven an explosion of interest about their societal impacts. Much of the discourse around how they will impact social equity has been cautionary or negative, focusing on questions like "how…

As large language models take on growing roles as automated evaluators in practical settings, a critical question arises: Can individuals persuade an LLM judge to assign unfairly high scores? This study is the first to reveal that…

Computation and Language · Computer Science 2025-08-12 Yerin Hwang , Dongryeol Lee , Taegwan Kang , Yongil Kim , Kyomin Jung

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Computation and Language · Computer Science 2024-12-17 Tao Zhang , Ziqian Zeng , Yuxiang Xiao , Huiping Zhuang , Cen Chen , James Foulds , Shimei Pan

Large Language Models (LLMs) have become integral to Software Engineering (SE), increasingly used in development workflows. However, their widespread adoption raises concerns about the presence and propagation of toxic language - harmful or…

Machine Learning · Computer Science 2026-01-21 Hao Zhuo , Yicheng Yang , Kewen Peng

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Cryptography and Security · Computer Science 2023-08-21 Xiangyu Qi , Kaixuan Huang , Ashwinee Panda , Peter Henderson , Mengdi Wang , Prateek Mittal

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Cryptography and Security · Computer Science 2025-07-15 Joshua Kazdan , Abhay Puri , Rylan Schaeffer , Lisa Yu , Chris Cundy , Jason Stanley , Sanmi Koyejo , Krishnamurthy Dvijotham

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song