English
Related papers

Related papers: Defending Pre-trained Language Models as Few-shot …

200 papers

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many…

Cryptography and Security · Computer Science 2024-12-23 Borja Molina-Coronado

While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…

Machine Learning · Computer Science 2022-03-15 Pengfei Xia , Hongjing Niu , Ziqiang Li , Bin Li

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models. However, the…

Cryptography and Security · Computer Science 2022-04-14 Huming Qiu , Hua Ma , Zhi Zhang , Alsharif Abuadbba , Wei Kang , Anmin Fu , Yansong Gao

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 visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial…

Machine Learning · Computer Science 2021-08-02 Mustafa Safa Ozdayi , Murat Kantarcioglu , Yulia R. Gel

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Artificial Intelligence · Computer Science 2023-10-31 Leo Schwinn , David Dobre , Stephan Günnemann , Gauthier Gidel

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

Cryptography and Security · Computer Science 2025-08-05 Nilufer Gulciftci , M. Emre Gursoy

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Computation and Language · Computer Science 2023-05-30 Xuanjie Fang , Sijie Cheng , Yang Liu , Wei Wang

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrations to efficiently…

Computation and Language · Computer Science 2024-10-31 Xiaosen Zheng , Tianyu Pang , Chao Du , Qian Liu , Jing Jiang , Min Lin

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

Recently, DL has been exploited in wireless communications such as modulation classification. However, due to the openness of wireless channel and unexplainability of DL, it is also vulnerable to adversarial attacks. In this correspondence,…

Signal Processing · Electrical Eng. & Systems 2023-06-21 Yunsong Huang , Weicheng Liu , Hui-Ming Wang

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Cryptography and Security · Computer Science 2024-01-31 Jie Li , Yi Liu , Chongyang Liu , Ling Shi , Xiaoning Ren , Yaowen Zheng , Yang Liu , Yinxing Xue

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Machine Learning · Computer Science 2025-09-29 Sujeevan Aseervatham , Achraf Kerzazi , Younès Bennani

Large pre-trained language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields,…

Computation and Language · Computer Science 2023-04-24 Tianhao Li , Sandesh Shetty , Advaith Kamath , Ajay Jaiswal , Xianqian Jiang , Ying Ding , Yejin Kim

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerable to backdoor…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Hritik Bansal , Nishad Singhi , Yu Yang , Fan Yin , Aditya Grover , Kai-Wei Chang

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

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained…

Computation and Language · Computer Science 2025-04-15 Xiaomei Zhang , Zhaoxi Zhang , Yanjun Zhang , Xufei Zheng , Leo Yu Zhang , Shengshan Hu , Shirui Pan

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Machine Learning · Computer Science 2024-07-17 Quang H. Nguyen , Nguyen Ngoc-Hieu , The-Anh Ta , Thanh Nguyen-Tang , Kok-Seng Wong , Hoang Thanh-Tung , Khoa D. Doan