English
Related papers

Related papers: Concept-ROT: Poisoning Concepts in Large Language …

200 papers

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively…

Cryptography and Security · Computer Science 2020-03-31 Adnan Siraj Rakin , Zhezhi He , Deliang Fan

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 widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for…

Computation and Language · Computer Science 2025-10-14 Ruizhe Zhu

Topic modeling is traditionally applied to word counts without accounting for the context in which words appear. Recent advancements in large language models (LLMs) offer contextualized word embeddings, which capture deeper meaning and…

Machine Learning · Statistics 2025-12-30 Morgane Austern , Yuanchuan Guo , Zheng Tracy Ke , Tianle Liu

Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment. Existing methods to mitigate bias lack a comprehensive understanding of its mechanisms or compromise the model's core capabilities. To…

Computation and Language · Computer Science 2025-01-27 Zeping Yu , Sophia Ananiadou

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

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Haripriya Harikumar , Vuong Le , Santu Rana , Sourangshu Bhattacharya , Sunil Gupta , Svetha Venkatesh

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model editing methods, which focus on modifying LLMs in a post-hoc…

Computation and Language · Computer Science 2024-02-22 Jianhao Yan , Futing Wang , Yafu Li , Yue Zhang

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Computation and Language · Computer Science 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

Cryptography and Security · Computer Science 2026-05-01 Mahshid Rezakhani , Nowfel Mashnoor , Kimia Azar , Hadi Kamali

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that…

Cryptography and Security · Computer Science 2022-02-16 Jie Wang , Ghulam Mubashar Hassan , Naveed Akhtar

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…

Cryptography and Security · Computer Science 2025-06-30 Stanley Wu , Ronik Bhaskar , Anna Yoo Jeong Ha , Shawn Shan , Haitao Zheng , Ben Y. Zhao

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…

Cryptography and Security · Computer Science 2025-06-10 Neil Fendley , Edward W. Staley , Joshua Carney , William Redman , Marie Chau , Nathan Drenkow

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

Artificial Intelligence · Computer Science 2025-10-21 Zhehao Zhang , Weijie Xu , Shixian Cui , Chandan K. Reddy

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

Computation and Language · Computer Science 2024-08-23 Nura Aljaafari , Danilo S. Carvalho , André Freitas

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Computation and Language · Computer Science 2025-12-01 Zhaoxin Zhang , Borui Chen , Yiming Hu , Youyang Qu , Tianqing Zhu , Longxiang Gao

Knowledge editing has emerged as an efficient technique for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there is a lack of effective measures to prevent the malicious…

Computation and Language · Computer Science 2025-05-27 Xiaopeng Li , Shasha Li , Shangwen Wang , Shezheng Song , Bin Ji , Huijun Liu , Jun Ma , Jie Yu

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these…

Artificial Intelligence · Computer Science 2024-10-25 Qi Li , Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Xinglin Pan , Xiaowen Chu

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