English
Related papers

Related papers: Impart: An Imperceptible and Effective Label-Speci…

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

Backdoor attacks involve the injection of a limited quantity of poisoned examples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when…

Cryptography and Security · Computer Science 2024-06-25 Hanfeng Xia , Haibo Hong , Ruili Wang

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

Cryptography and Security · Computer Science 2025-06-17 Mengyuan Sun , Yu Li , Yuchen Liu , Bo Du , Yunjie Ge

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of…

Cryptography and Security · Computer Science 2019-03-01 Mauro Barni , Kassem Kallas , Benedetta Tondi

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…

Cryptography and Security · Computer Science 2022-01-04 Phillip Rieger , Thien Duc Nguyen , Markus Miettinen , Ahmad-Reza Sadeghi

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Machine Learning · Computer Science 2020-08-11 Shuo Wang , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen , Tianle Chen

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

Class incremental learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, it has been shown that such approaches are…

Machine Learning · Computer Science 2023-05-01 Muhammad Umer , Robi Polikar

With the widespread application of deep learning across various domains, concerns about its security have grown significantly. Among these, backdoor attacks pose a serious security threat to deep neural networks (DNNs). In recent years,…

Cryptography and Security · Computer Science 2024-03-21 Wenmin Chen , Xiaowei Xu

In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…

Machine Learning · Computer Science 2022-02-10 Muhammad Umer , Robi Polikar

Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Tong Wu , Tianhao Wang , Vikash Sehwag , Saeed Mahloujifar , Prateek Mittal

\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

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

Cryptography and Security · Computer Science 2026-02-06 Zihan Wang , Hongwei Li , Rui Zhang , Wenbo Jiang , Guowen Xu

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Cryptography and Security · Computer Science 2024-12-30 A. Dilara Yavuz , M. Emre Gursoy

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…

Machine Learning · Computer Science 2022-10-25 KiYoon Yoo , Nojun Kwak

Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack…

Cryptography and Security · Computer Science 2021-10-06 Xiaoyi Chen , Ahmed Salem , Dingfan Chen , Michael Backes , Shiqing Ma , Qingni Shen , Zhonghai Wu , Yang Zhang

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these…

Cryptography and Security · Computer Science 2024-09-04 Jinghuai Zhang , Jianfeng Chi , Zheng Li , Kunlin Cai , Yang Zhang , Yuan Tian

In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test…

Machine Learning · Computer Science 2022-10-13 Jonathan Hayase , Sewoong Oh

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

Machine Learning · Computer Science 2024-09-10 Alkis Kalavasis , Amin Karbasi , Argyris Oikonomou , Katerina Sotiraki , Grigoris Velegkas , Manolis Zampetakis