English
Related papers

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

200 papers

What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…

Computation and Language · Computer Science 2026-02-10 Jasmine Cui , Charles Ye

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Computation and Language · Computer Science 2023-12-27 Xuan Sheng , Zhicheng Li , Zhaoyang Han , Xiangmao Chang , Piji Li

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Cryptography and Security · Computer Science 2023-02-09 Yujin Huang , Terry Yue Zhuo , Qiongkai Xu , Han Hu , Xingliang Yuan , Chunyang Chen

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the…

Computation and Language · Computer Science 2026-03-24 J. Ben Tamo , Daniel Carlander-Reuterfelt , Jonathan Rubin , Dezhi Hong , Mingxian Wang , Oleg Poliannikov

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Computation and Language · Computer Science 2026-05-04 Gregory N. Frank

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

Cryptography and Security · Computer Science 2024-10-08 Lu Yan , Siyuan Cheng , Xuan Chen , Kaiyuan Zhang , Guangyu Shen , Zhuo Zhang , Xiangyu Zhang

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Cryptography and Security · Computer Science 2024-10-01 Qin Liu , Wenjie Mo , Terry Tong , Jiashu Xu , Fei Wang , Chaowei Xiao , Muhao Chen

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Cryptography and Security · Computer Science 2025-10-01 Miao Yu , Zhenhong Zhou , Moayad Aloqaily , Kun Wang , Biwei Huang , Stephen Wang , Yueming Jin , Qingsong Wen

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Cryptography and Security · Computer Science 2026-04-15 Haotian Jin , Yang Li , Haihui Fan , Lin Shen , Xiangfang Li , Bo Li

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has…

Computation and Language · Computer Science 2023-10-10 Xiaofei Sun , Xiaoya Li , Yuxian Meng , Xiang Ao , Lingjuan Lyu , Jiwei Li , Tianwei Zhang

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…

Computation and Language · Computer Science 2021-06-14 Fanchao Qi , Yuan Yao , Sophia Xu , Zhiyuan Liu , Maosong Sun

A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally new attack surface. ThoughtSteer perturbs a single embedding…

Machine Learning · Computer Science 2026-04-02 Swapnil Parekh

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…

Computation and Language · Computer Science 2021-10-07 Kangjie Chen , Yuxian Meng , Xiaofei Sun , Shangwei Guo , Tianwei Zhang , Jiwei Li , Chun Fan

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Computation and Language · Computer Science 2021-03-30 Wenkai Yang , Lei Li , Zhiyuan Zhang , Xuancheng Ren , Xu Sun , Bin He

In this paper, we delve into several mechanisms employed by Transformer-based language models (LLMs) for factual recall tasks. We outline a pipeline consisting of three major steps: (1) Given a prompt ``The capital of France is,''…

Computation and Language · Computer Science 2024-05-27 Ang Lv , Yuhan Chen , Kaiyi Zhang , Yulong Wang , Lifeng Liu , Ji-Rong Wen , Jian Xie , Rui Yan

Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let…

Computation and Language · Computer Science 2024-04-23 Sachin Goyal , Ziwei Ji , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar , Vaishnavh Nagarajan