English
Related papers

Related papers: Merging Triggers, Breaking Backdoors: Defensive Po…

200 papers

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

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

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…

In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected…

Cryptography and Security · Computer Science 2025-05-07 Zihan Wang , Hongwei Li , Rui Zhang , Wenbo Jiang , Kangjie Chen , Tianwei Zhang , Qingchuan Zhao , Guowen Xu

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…

Cryptography and Security · Computer Science 2025-08-05 Man Hu , Yahui Ding , Yatao Yang , Liangyu Chen , Yanhao Jia , Shuai Zhao

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Cryptography and Security · Computer Science 2026-03-23 Shawn Li , Yue Zhao

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment…

Cryptography and Security · Computer Science 2025-12-18 Jing Cui , Yufei Han , Jianbin Jiao , Junge Zhang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…

Cryptography and Security · Computer Science 2024-12-03 Jing Cui , Yishi Xu , Zhewei Huang , Shuchang Zhou , Jianbin Jiao , Junge Zhang

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…

Machine Learning · Computer Science 2022-10-25 KiYoon Yoo , Nojun Kwak

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

Cryptography and Security · Computer Science 2025-10-20 Adam Swanda , Amy Chang , Alexander Chen , Fraser Burch , Paul Kassianik , Konstantin Berlin

Model merging for Large Language Models (LLMs) directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on…

Cryptography and Security · Computer Science 2025-05-30 Zenghui Yuan , Yangming Xu , Jiawen Shi , Pan Zhou , Lichao Sun

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Machine Learning · Computer Science 2024-08-27 Alina Ermilova , Elizaveta Kovtun , Dmitry Berestnev , Alexey Zaytsev

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

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

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 Models (LLMS) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for generating content that could be deemed harmful. To mitigate these…

Cryptography and Security · Computer Science 2024-05-20 Zihao Xu , Yi Liu , Gelei Deng , Yuekang Li , Stjepan Picek

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

Computation and Language · Computer Science 2025-02-25 Daniil Khomsky , Narek Maloyan , Bulat Nutfullin

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi