English
Related papers

Related papers: Not All Prompts Are Secure: A Switchable Backdoor …

200 papers

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yong Li , Han Gao

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Aniruddha Saha , Ajinkya Tejankar , Soroush Abbasi Koohpayegani , Hamed Pirsiavash

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Cryptography and Security · Computer Science 2025-03-28 Dorde Popovic , Amin Sadeghi , Ting Yu , Sanjay Chawla , Issa Khalil

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…

Computation and Language · Computer Science 2021-10-07 Kangjie Chen , Yuxian Meng , Xiaofei Sun , Shangwei Guo , Tianwei Zhang , Jiwei Li , Chun Fan

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chongxin Li , Hanzhang Wang , Lian Duan

Backdoor attacks pose severe security threats to deep neural networks by embedding malicious triggers that force misclassification. While machine unlearning techniques can remove backdoor behaviors, current methods lack transparency and…

Cryptography and Security · Computer Science 2025-11-27 Tien Dat Hoang

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

Cryptography and Security · Computer Science 2025-12-10 Jianyao Yin , Luca Arnaboldi , Honglong Chen , Pascal Berrang , Mark Ryan

Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown to be vulnerable to…

Machine Learning · Computer Science 2024-04-02 Xiaopeng Xie , Ming Yan , Xiwen Zhou , Chenlong Zhao , Suli Wang , Yong Zhang , Joey Tianyi Zhou

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

Computation and Language · Computer Science 2026-05-28 Snehasis Mukhopadhyay

Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…

Cryptography and Security · Computer Science 2024-08-22 Jiahao Wang , Xianglong Zhang , Xiuzhen Cheng , Pengfei Hu , Guoming Zhang

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Computation and Language · Computer Science 2021-03-30 Wenkai Yang , Lei Li , Zhiyuan Zhang , Xuancheng Ren , Xu Sun , Bin He

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Machine Learning · Computer Science 2026-03-31 Osama Wehbi , Sarhad Arisdakessian , Omar Abdel Wahab , Azzam Mourad , Hadi Otrok , Jamal Bentahar

We present a new type of backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) that has been previously unstudied. In particular, we examine the application of facial recognition. Deep learning techniques are…

Computer Vision and Pattern Recognition · Computer Science 2018-12-10 Jacob Dumford , Walter Scheirer

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be easily countered by…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Siyuan Liang , Mingli Zhu , Aishan Liu , Baoyuan Wu , Xiaochun Cao , Ee-Chien Chang

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled…

Cryptography and Security · Computer Science 2022-05-17 Ying He , Zhili Shen , Chang Xia , Jingyu Hua , Wei Tong , Sheng Zhong

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…

Cryptography and Security · Computer Science 2026-04-07 Yuhan Shui , Ruobin Jin , Zhihao Dou , Zhiqiang Gao

Backdoors pose a serious threat to machine learning, as they can compromise the integrity of security-critical systems, such as self-driving cars. While different defenses have been proposed to address this threat, they all rely on the…

Cryptography and Security · Computer Science 2025-02-04 Alexander Warnecke , Julian Speith , Jan-Niklas Möller , Konrad Rieck , Christof Paar

Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning…

Cryptography and Security · Computer Science 2026-04-13 Akshit Jindal , Saket Anand , Chetan Arora , Vikram Goyal

Backdoor (Trojan) attacks are emerging threats against deep neural networks (DNN). A DNN being attacked will predict to an attacker-desired target class whenever a test sample from any source class is embedded with a backdoor pattern; while…

Cryptography and Security · Computer Science 2021-12-08 Xi Li , Zhen Xiang , David J. Miller , George Kesidis