English
Related papers

Related papers: ASIDE: Architectural Separation of Instructions an…

200 papers

By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer…

Machine Learning · Computer Science 2023-03-13 Yongchao Zhou , Andrei Ioan Muresanu , Ziwen Han , Keiran Paster , Silviu Pitis , Harris Chan , Jimmy Ba

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 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

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this…

Computation and Language · Computer Science 2026-03-26 Fangyu Ding , Ding Ding , Sijin Chen , Kaibo Wang , Peng Xu , Zijin Feng , Haoli Bai , Kai Han , Youliang Yan , Binhang Yuan , Jiacheng Sun

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Computation and Language · Computer Science 2025-12-09 Sebastian Sztwiertnia , Felix Friedrich , Kristian Kersting , Patrick Schramowski , Björn Deiseroth

Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment…

Computation and Language · Computer Science 2024-10-25 Yunjia Qi , Hao Peng , Xiaozhi Wang , Bin Xu , Lei Hou , Juanzi Li

Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt…

Computation and Language · Computer Science 2024-03-12 Wangtao Sun , Haotian Xu , Xuanqing Yu , Pei Chen , Shizhu He , Jun Zhao , Kang Liu

The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network…

Computation and Language · Computer Science 2019-12-03 Van Tung Pham , Haihua Xu , Yerbolat Khassanov , Zhiping Zeng , Eng Siong Chng , Chongjia Ni , Bin Ma , Haizhou Li

We present SEED, an elaborate image tokenizer that empowers Large Language Models (LLMs) with the emergent ability to SEE and Draw at the same time. Research on image tokenizers has previously reached an impasse, as frameworks employing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Yuying Ge , Yixiao Ge , Ziyun Zeng , Xintao Wang , Ying Shan

Obfuscation of computer programs has historically been approached either as a practical but \textit{ad hoc} craft to make reverse engineering subjectively difficult, or as a sound theoretical investigation unfortunately detached from the…

Cryptography and Security · Computer Science 2024-11-11 Ali Ajorian , Erick Lavoie , Christian Tschudin

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Computation and Language · Computer Science 2025-08-29 Chen Chen , Yuchen Sun , Jiaxin Gao , Xueluan Gong , Qian Wang , Ziyao Wang , Yongsen Zheng , Kwok-Yan Lam

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Cryptography and Security · Computer Science 2018-08-31 Cong Liao , Haoti Zhong , Anna Squicciarini , Sencun Zhu , David Miller

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…

Cryptography and Security · Computer Science 2024-03-21 Yanzhou Li , Tianlin Li , Kangjie Chen , Jian Zhang , Shangqing Liu , Wenhan Wang , Tianwei Zhang , Yang Liu

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

Cryptography and Security · Computer Science 2026-02-27 Qianlong Lan , Anuj Kaul , Shaun Jones , Stephanie Westrum

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

Computation and Language · Computer Science 2026-02-04 Patrick Cooper , Alireza Nadali , Ashutosh Trivedi , Alvaro Velasquez

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Cryptography and Security · Computer Science 2025-05-01 Ruochen Jiao , Shaoyuan Xie , Justin Yue , Takami Sato , Lixu Wang , Yixuan Wang , Qi Alfred Chen , Qi Zhu

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Artificial Intelligence · Computer Science 2026-05-12 Dongcheng Zhang , Yi Zhang , Yuxin Chen , An Zhang , Xiang Wang , Chaochao Lu

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Cryptography and Security · Computer Science 2025-11-11 Haonan Shi , Guoli Wang , Tu Ouyang , An Wang