English
Related papers

Related papers: Language-Switching Triggers Take a Latent Detour T…

200 papers

Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of language-switching backdoors,…

Computation and Language · Computer Science 2026-02-16 Théo Lasnier , Wissam Antoun , Francis Kulumba , Djamé Seddah

We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understanding how language models function and the origins of…

Computation and Language · Computer Science 2024-06-12 Chris Wendler , Veniamin Veselovsky , Giovanni Monea , Robert West

Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B…

Computation and Language · Computer Science 2025-08-25 Mohammed Abu Baker , Lakshmi Babu-Saheer

Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. A popular user-facing application of LLMs is the…

Computation and Language · Computer Science 2024-10-29 Terry Tong , Jiashu Xu , Qin Liu , Muhao Chen

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when…

Machine Learning · Computer Science 2024-05-07 Max Lamparth , Anka Reuel

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

Computation and Language · Computer Science 2021-09-29 Shaofeng Li , Hui Liu , Tian Dong , Benjamin Zi Hao Zhao , Minhui Xue , Haojin Zhu , Jialiang Lu

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

Computation and Language · Computer Science 2025-03-18 Xuanli He , Jun Wang , Qiongkai Xu , Pasquale Minervini , Pontus Stenetorp , Benjamin I. P. Rubinstein , Trevor Cohn

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Cryptography and Security · Computer Science 2025-02-18 Huaizhi Ge , Yiming Li , Qifan Wang , Yongfeng Zhang , Ruixiang Tang

We explore \textbf{C}ross-lingual \textbf{B}ackdoor \textbf{AT}tacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can automatically transfer to others through shared embedding…

Computation and Language · Computer Science 2025-10-07 Himanshu Beniwal , Sailesh Panda , Birudugadda Srivibhav , Mayank Singh

Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-end; how information flows through the pipeline remains…

Computation and Language · Computer Science 2026-04-08 Alexandrine Fortier , Thomas Thebaud , Jesús Villalba , Najim Dehak , Patrick Cardinal , Peter West

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Cryptography and Security · Computer Science 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan

The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high…

Cryptography and Security · Computer Science 2023-09-07 Haomiao Yang , Kunlan Xiang , Mengyu Ge , Hongwei Li , Rongxing Lu , Shui Yu

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

Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…

Cryptography and Security · Computer Science 2024-04-04 Yunzhuo Hao , Wenkai Yang , Yankai Lin

Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…

Cryptography and Security · Computer Science 2025-04-01 Jingyi Zheng , Tianyi Hu , Tianshuo Cong , Xinlei He

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Cryptography and Security · Computer Science 2026-05-15 Rui Wen , Mark Russinovich , Andrew Paverd , Jun Sakuma , Ahmed Salem
‹ Prev 1 2 3 10 Next ›