English
Related papers

Related papers: Inverting Trojans in LLMs

200 papers

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Computation and Language · Computer Science 2026-05-14 Liang Lin , Miao Yu , Moayad Aloqaily , Zhenhong Zhou , Kun Wang , Linsey Pang , Prakhar Mehrotra , Qingsong Wen

This position paper argues that the AI/ML community should stop overclaiming and retire the label "positive backdoor," and instead treat trigger-activated hidden behaviors as Secret Alignment. Crucially, protective claims based on Secret…

Cryptography and Security · Computer Science 2026-05-28 Jianwei Li , Jung-Eun Kim

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…

Computation and Language · Computer Science 2026-04-28 Honglin Mu , Jinghao Liu , Kaiyang Wan , Rui Xing , Xiuying Chen , Timothy Baldwin , Wanxiang Che

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

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make…

Cryptography and Security · Computer Science 2021-03-25 Yinpeng Dong , Xiao Yang , Zhijie Deng , Tianyu Pang , Zihao Xiao , Hang Su , Jun Zhu

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains…

Cryptography and Security · Computer Science 2023-09-06 Arezoo Rajabi , Surudhi Asokraj , Fengqing Jiang , Luyao Niu , Bhaskar Ramasubramanian , Jim Ritcey , Radha Poovendran

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Cryptography and Security · Computer Science 2024-06-11 Yuanpu Cao , Bochuan Cao , Jinghui Chen

Deep Learning (DL) has become a key technology that assists radio frequency (RF) signal classification applications, such as modulation classification. However, the DL models are vulnerable to adversarial machine learning threats, such as…

Cryptography and Security · Computer Science 2026-03-27 Younes Salmi , Hanna Bogucka

The large language model (LLM) powered recommendation paradigm has been proposed to address the limitations of traditional recommender systems, which often struggle to handle cold start users or items with new IDs. Despite its…

Information Retrieval · Computer Science 2025-09-15 Yubo Wang , Min Tang , Nuo Shen , Shujie Cui , Weiqing Wang

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

Robots need task planning methods to achieve goals that require more than individual actions. Recently, large language models (LLMs) have demonstrated impressive performance in task planning. LLMs can generate a step-by-step solution using…

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…

Cryptography and Security · Computer Science 2024-06-25 Filippo Galli , Luca Melis , Tommaso Cucinotta

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…

Cryptography and Security · Computer Science 2024-12-05 Pengzhou Cheng , Zongru Wu , Wei Du , Haodong Zhao , Wei Lu , Gongshen Liu

Recent empirical results have sparked a debate about whether or not Large Language Models (LLMs) are capable of Theory of Mind (ToM). While some have found LLMs to be successful on ToM evaluations such as the False Belief task, others have…

Computation and Language · Computer Science 2025-05-29 Zhiqiang Pi , Annapurna Vadaparty , Benjamin K. Bergen , Cameron R. Jones

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

Cryptography and Security · Computer Science 2025-05-05 Wenjie Qu , Yuguang Zhou , Yongji Wu , Tingsong Xiao , Binhang Yuan , Yiming Li , Jiaheng Zhang

Effective problem solving with Large Language Models (LLMs) can be enhanced when they are paired with external search algorithms. By viewing the space of diverse ideas and their follow-up possibilities as a tree structure, the search…

Machine Learning · Computer Science 2026-03-27 Jungtaek Kim , Thomas Zeng , Ziqian Lin , Minjae Lee , Chungpa Lee , Jy-yong Sohn , Hyung Il Koo , Kangwook Lee

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

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts…

Cryptography and Security · Computer Science 2026-05-12 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Yuzhe Huang , Haichang Gao