English
Related papers

Related papers: ConfGuard: A Simple and Effective Backdoor Detecti…

200 papers

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhifang Zhang , Bojun Yang , Shuo He , Weitong Chen , Wei Emma Zhang , Olaf Maennel , Lei Feng , Miao Xu

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Computation and Language · Computer Science 2026-04-06 Zhexin Zhang , Yuhao Sun , Junxiao Yang , Shiyao Cui , Yuanchao Zhang , Hongning Wang , Minlie Huang

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

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Cryptography and Security · Computer Science 2025-11-18 Hasini Jayathilaka

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code.…

Cryptography and Security · Computer Science 2025-06-23 Xinghang Li , Jingzhe Ding , Chao Peng , Bing Zhao , Xiang Gao , Hongwan Gao , Xinchen Gu

Large language models (LLMs) enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak…

Cryptography and Security · Computer Science 2026-01-26 Guorui Chen , Yifan Xia , Xiaojun Jia , Zhijiang Li , Philip Torr , Jindong Gu

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for…

Machine Learning · Computer Science 2023-12-19 Yihang Lin , Pengyuan Zhou , Zhiqian Wu , Yong Liao

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) tasks but also pose ethical and societal risks due to their propensity to generate harmful content. Existing methods have limitations, including the…

Computation and Language · Computer Science 2025-05-22 Ximing Dong , Dayi Lin , Shaowei Wang , Ahmed E. Hassan

Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often turn to (untrustworthy) third-party services, such as…

Cryptography and Security · Computer Science 2025-10-31 Xi Li , Ruofan Mao , Yusen Zhang , Renze Lou , Chen Wu , Jiaqi Wang

Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited…

Cryptography and Security · Computer Science 2025-11-17 Yupei Liu , Yanting Wang , Yuqi Jia , Jinyuan Jia , Neil Zhenqiang Gong

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shuhan Xu , Siyuan Liang , Hongling Zheng , Aishan Liu , Xinbiao Wang , Yong Luo , Fu Lin , Leszek Rutkowski , Dacheng Tao

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Cryptography and Security · Computer Science 2026-05-20 Hongyu Cai , Arjun Arunasalam , Yiming Liang , Antonio Bianchi , Z. Berkay Celik

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

Cryptography and Security · Computer Science 2025-10-06 Qianshan Wei , Tengchao Yang , Yaochen Wang , Xinfeng Li , Lijun Li , Zhenfei Yin , Yi Zhan , Thorsten Holz , Zhiqiang Lin , XiaoFeng Wang

Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backdoor implantation during supervised fine-tuning and will…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Tianmeng Fang , Yong Wang , Zetai Kong , Zengzhen Su , Jun Wang , Chengjin Yu , Wei Wang

Federated Learning (FL) is a promising approach enabling multiple clients to train Deep Neural Networks (DNNs) collaboratively without sharing their local training data. However, FL is susceptible to backdoor (or targeted poisoning)…

Cryptography and Security · Computer Science 2023-08-23 Phillip Rieger , Torsten Krauß , Markus Miettinen , Alexandra Dmitrienko , Ahmad-Reza Sadeghi

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…

Computation and Language · Computer Science 2025-07-28 Yuanhe Zhang , Fangzhou Xie , Zhenhong Zhou , Zherui Li , Hao Chen , Kun Wang , Yufei Guo

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

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Computation and Language · Computer Science 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh