English
Related papers

Related papers: NOTABLE: Transferable Backdoor Attacks Against Pro…

200 papers

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Cryptography and Security · Computer Science 2024-09-09 Gorka Abad , Stjepan Picek , Lorenzo Cavallaro , Aitor Urbieta

In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial…

Machine Learning · Computer Science 2024-05-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Computation and Language · Computer Science 2024-07-08 Xinglin Li , Xianwen He , Yao Li , Minhao Cheng

With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task…

Computation and Language · Computer Science 2024-08-22 Ziqiang Li , Yueqi Zeng , Pengfei Xia , Lei Liu , Zhangjie Fu , Bin Li

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Machine Learning · Computer Science 2020-06-22 I. Fursov , A. Zaytsev , N. Kluchnikov , A. Kravchenko , E. Burnaev

Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern. These attacks involve the subtle insertion of triggers…

Cryptography and Security · Computer Science 2025-09-18 Bart Pleiter , Behrad Tajalli , Stefanos Koffas , Gorka Abad , Jing Xu , Martha Larson , Stjepan Picek

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Meiwen Ding , Song Xia , Chenqi Kong , Xudong Jiang

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or…

Machine Learning · Computer Science 2025-05-27 Shijie Liu , Andrew C. Cullen , Paul Montague , Sarah Erfani , Benjamin I. P. Rubinstein

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

Artificial Intelligence · Computer Science 2025-09-10 Minghui Li , Hao Zhang , Yechao Zhang , Wei Wan , Shengshan Hu , pei Xiaobing , Jing Wang

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Haripriya Harikumar , Vuong Le , Santu Rana , Sourangshu Bhattacharya , Sunil Gupta , Svetha Venkatesh

Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…

Machine Learning · Computer Science 2025-09-24 Zhaoxin Wang , Handing Wang , Cong Tian , Yaochu Jin

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download weights of models pre-trained on large datasets, then fine-tune the weights on a task of their choice. This raises the question of whether downloading…

Machine Learning · Computer Science 2020-04-15 Keita Kurita , Paul Michel , Graham Neubig

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Machine Learning · Statistics 2018-02-28 Lei Wu , Zhanxing Zhu , Cheng Tai , Weinan E

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

Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the goal of the attacker is to use poisoned updates to implant…

Cryptography and Security · Computer Science 2022-06-22 Zhengming Zhang , Ashwinee Panda , Linyue Song , Yaoqing Yang , Michael W. Mahoney , Joseph E. Gonzalez , Kannan Ramchandran , Prateek Mittal

Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yi Yu , Yufei Wang , Wenhan Yang , Lanqing Guo , Shijian Lu , Ling-Yu Duan , Yap-Peng Tan , Alex C. Kot

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