English
Related papers

Related papers: Analyzing And Editing Inner Mechanisms Of Backdoor…

200 papers

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…

Computation and Language · Computer Science 2026-05-13 Ziyu Liu , Tao Li , Tianjie Ni , Xiaolong Lan , Wengang Ma , Tao Yang , Guohua Wang , Junjiang He

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Cryptography and Security · Computer Science 2024-03-13 Hongwei Zhang , Xiaoyin Xu , Dongsheng An , Xianfeng Gu , Min Zhang

Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in the static text…

Cryptography and Security · Computer Science 2024-09-12 Rui Zeng , Xi Chen , Yuwen Pu , Xuhong Zhang , Tianyu Du , Shouling Ji

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Artificial Intelligence · Computer Science 2024-10-29 Dongliang Guo , Mengxuan Hu , Zihan Guan , Junfeng Guo , Thomas Hartvigsen , Sheng Li

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

Cryptography and Security · Computer Science 2024-12-25 Sara Price , Arjun Panickssery , Sam Bowman , Asa Cooper Stickland

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…

Cryptography and Security · Computer Science 2022-04-13 Shaik Mohammed Maqsood , Viveros Manuela Ceron , Addluri GowthamKrishna

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

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

In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…

Cryptography and Security · Computer Science 2025-01-07 Yidong Ding , Jiafei Niu , Ping Yi

The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating…

Machine Learning · Computer Science 2025-01-29 Ajesh Koyatan Chathoth , Stephen Lee

\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are…

Cryptography and Security · Computer Science 2021-09-01 Linyang Li , Demin Song , Xiaonan Li , Jiehang Zeng , Ruotian Ma , Xipeng Qiu

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

Computation and Language · Computer Science 2024-09-24 Zhenting Wang , Zhizhi Wang , Mingyu Jin , Mengnan Du , Juan Zhai , Shiqing Ma

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

Computation and Language · Computer Science 2021-06-04 Fanchao Qi , Mukai Li , Yangyi Chen , Zhengyan Zhang , Zhiyuan Liu , Yasheng Wang , Maosong Sun

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Cryptography and Security · Computer Science 2017-12-18 Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , Dawn Song

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

Computation and Language · Computer Science 2023-05-29 Xuanli He , Jun Wang , Benjamin Rubinstein , Trevor Cohn

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

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Cryptography and Security · Computer Science 2025-10-21 Zongze Li , Jiawei Guo , Haipeng Cai

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

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Machine Learning · Computer Science 2022-06-17 Mikel Bober-Irizar , Ilia Shumailov , Yiren Zhao , Robert Mullins , Nicolas Papernot