English
Related papers

Related papers: Rethinking Backdoor Detection Evaluation for Langu…

200 papers

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Machine Learning · Computer Science 2022-05-03 Yang Li , Quan Pan , Erik Cambria

Trojan backdoors can be injected into large language models at various stages, including pretraining, fine-tuning, and in-context learning, posing a significant threat to the model's alignment. Due to the nature of causal language modeling,…

Computation and Language · Computer Science 2025-01-22 Vedant Bhasin , Matthew Yudin , Razvan Stefanescu , Rauf Izmailov

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Multiagent Systems · Computer Science 2022-11-22 Shuo Chen , Yue Qiu , Jie Zhang

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has…

Computation and Language · Computer Science 2023-10-10 Xiaofei Sun , Xiaoya Li , Yuxian Meng , Xiang Ao , Lingjuan Lyu , Jiwei Li , Tianwei Zhang

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

Computation and Language · Computer Science 2024-06-04 Ansh Arora , Xuanli He , Maximilian Mozes , Srinibas Swain , Mark Dras , Qiongkai Xu

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

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Xiaoxuan Han , Songlin Yang , Wei Wang , Ziwen He , Jing Dong

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Cryptography and Security · Computer Science 2023-10-30 Lu Yan , Zhuo Zhang , Guanhong Tao , Kaiyuan Zhang , Xuan Chen , Guangyu Shen , Xiangyu Zhang

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Machine Learning · Computer Science 2021-04-26 Jonathan Hayase , Weihao Kong , Raghav Somani , Sewoong Oh

Generative large language models are crucial in natural language processing, but they are vulnerable to backdoor attacks, where subtle triggers compromise their behavior. Although backdoor attacks against LLMs are constantly emerging,…

Cryptography and Security · Computer Science 2025-02-27 Xuxu Liu , Siyuan Liang , Mengya Han , Yong Luo , Aishan Liu , Xiantao Cai , Zheng He , Dacheng Tao

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Cryptography and Security · Computer Science 2023-07-17 Zihao Zhu , Mingda Zhang , Shaokui Wei , Li Shen , Yanbo Fan , Baoyuan Wu

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and…

Machine Learning · Computer Science 2024-11-07 Todd Huster , Peter Lin , Razvan Stefanescu , Emmanuel Ekwedike , Ritu Chadha

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

Software Engineering · Computer Science 2025-10-17 Quoc Hung Le , Thanh Le-Cong , Bach Le , Bowen Xu

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Machine Learning · Computer Science 2025-04-08 Min Liu , Alberto Sangiovanni-Vincentelli , Xiangyu Yue

Genomic foundation models trained on DNA sequences have demonstrated remarkable capabilities across diverse biological tasks, from variant effect prediction to genome design. These models are typically trained on massive, publicly sourced…

Genomics · Quantitative Biology 2026-03-31 Charalampos Koilakos , Ioannis Mouratidis , Ilias Georgakopoulos-Soares

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…

Cryptography and Security · Computer Science 2026-02-04 Blake Bullwinkel , Giorgio Severi , Keegan Hines , Amanda Minnich , Ram Shankar Siva Kumar , Yonatan Zunger