English
Related papers

Related papers: Self-Purification Mitigates Backdoors in Multimoda…

200 papers

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Machine Learning · Computer Science 2025-08-08 Wenjie Huo , Katinka Wolter

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Xinxin Liu , Zhongliang Guo , Siyuan Huang , Chun Pong Lau

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…

Machine Learning · Computer Science 2024-06-04 Sen Li , Junchi Ma , Minhao Cheng

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and…

Cryptography and Security · Computer Science 2024-04-22 Beichen Li , Yuanfang Guo , Heqi Peng , Yangxi Li , Yunhong Wang

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…

Computation and Language · Computer Science 2024-12-11 Wangli Yang , Jie Yang , Yi Guo , Johan Barthelemy

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…

Computation and Language · Computer Science 2023-10-23 Xuanli He , Qiongkai Xu , Jun Wang , Benjamin Rubinstein , Trevor Cohn

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

Cryptography and Security · Computer Science 2024-09-10 Abdullah Arafat Miah , Yu Bi

Self-Supervised Learning (SSL) has become a prominent paradigm for pre-training encoders to learning general-purpose representations from unlabeled data and releasing them on third-party platforms for broad downstream deep learning tasks.…

Machine Learning · Computer Science 2026-02-02 TIngxu Han , Wei Song , Weisong Sun , Ziqi Ding , Yebo Feng , Chunrong Fang , Jun Li , Hanwei Qian , Zhenyu Chen , Yang Liu

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

Cryptography and Security · Computer Science 2024-01-10 Han Qiu , Yi Zeng , Shangwei Guo , Tianwei Zhang , Meikang Qiu , Bhavani Thuraisingham

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Alvin Chan , Yew-Soon Ong

Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when…

Machine Learning · Computer Science 2024-05-07 Max Lamparth , Anka Reuel

Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet underexplored challenge arises when such backdoors are…

Computation and Language · Computer Science 2025-10-01 Yao Tong , Weijun Li , Xuanli He , Haolan Zhan , Qiongkai Xu

The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…

Cryptography and Security · Computer Science 2024-06-26 Mohamed Amine Merzouk , Erwan Beurier , Reda Yaich , Nora Boulahia-Cuppens , Frédéric Cuppens

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Computation and Language · Computer Science 2023-12-19 Hongwei Yao , Jian Lou , Zhan Qin

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However, existing backdoor defenses are difficult to operationalize for Backdoor Defense-as-a-Service…

Cryptography and Security · Computer Science 2026-02-09 Chen Chen , Yuchen Sun , Jiaxin Gao , Yanwen Jia , Xueluan Gong , Qian Wang , Kwok-Yan Lam

Backdoor attacks undermine the integrity of machine learning models by allowing attackers to manipulate predictions using poisoned training data. Such attacks lead to targeted misclassification when specific triggers are present, while the…

Cryptography and Security · Computer Science 2025-02-12 Shaokui Wei , Jiayin Liu , Hongyuan Zha

Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak attacks in low-resource languages. Current safety alignment…

Machine Learning · Computer Science 2026-05-11 Ruiyang Qin , Qingzhuo Wang , Dongrui Liu , Qiang Li , Zhihua Wei , Wen Shen

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam