English
Related papers

Related papers: Pruning and Malicious Injection: A Retraining-Free…

200 papers

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

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed…

Computation and Language · Computer Science 2024-06-10 Tianrong Zhang , Zhaohan Xi , Ting Wang , Prasenjit Mitra , Jinghui Chen

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

Cryptography and Security · Computer Science 2026-04-24 Naheed Rayhan , Sohely Jahan

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and integrity. Fine-tuning based on benign data is a natural…

Artificial Intelligence · Computer Science 2023-10-31 Mingli Zhu , Shaokui Wei , Li Shen , Yanbo Fan , Baoyuan Wu

Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Hossein Mirzaei , Zeinab Taghavi , Sepehr Rezaee , Masoud Hadi , Moein Madadi , Mackenzie W. Mathis

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Machine Learning · Computer Science 2021-03-19 Todd Huster , Emmanuel Ekwedike

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks…

Machine Learning · Computer Science 2026-05-29 Yang Dai , Oubo Ma , Longfei Zhang , Xingxing Liang , Xiaochun Cao , Shouling Ji , Jiaheng Zhang , Jincai Huang , Li Shen

Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…

Cryptography and Security · Computer Science 2026-04-14 Weijun Li , Ansh Arora , Xuanli He , Mark Dras , Qiongkai Xu

In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious…

Machine Learning · Computer Science 2026-02-13 Dung Thuy Nguyen , Ngoc N. Tran , Taylor T. Johnson , Kevin Leach

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…

Cryptography and Security · Computer Science 2025-09-19 Gustavo Sandoval , Denys Fenchenko , Junyao Chen

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A…

Cryptography and Security · Computer Science 2026-05-01 Ching-Chun Chang , Kai Gao , Shuying Xu , Anastasia Kordoni , Christopher Leckie , Isao Echizen

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the…

Cryptography and Security · Computer Science 2022-07-05 Mingfu Xue , Can He , Shichang Sun , Jian Wang , Weiqiang Liu

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…

Cryptography and Security · Computer Science 2020-03-20 Erwin Quiring , Konrad Rieck

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

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

The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not everyone can be an attacker since the process of designing the…

Cryptography and Security · Computer Science 2023-09-06 Sze Jue Yang , Quang Nguyen , Chee Seng Chan , Khoa D. Doan

Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…

Cryptography and Security · Computer Science 2022-04-21 Maximilian Noppel , Lukas Peter , Christian Wressnegger

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Computation and Language · Computer Science 2023-01-26 Jiali Wei , Ming Fan , Wenjing Jiao , Wuxia Jin , Ting Liu

Precise future human motion prediction over sub-second horizons from past observations is crucial for various safety-critical applications. To date, only a few studies have examined the vulnerability of skeleton-based neural networks to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Chaohui Xu , Si Wang , Chip-Hong Chang