English
Related papers

Related papers: A Proxy Attack-Free Strategy for Practically Impro…

200 papers

Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…

Machine Learning · Computer Science 2022-03-15 Yinpeng Dong , Shuyu Cheng , Tianyu Pang , Hang Su , Jun Zhu

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing…

Cryptography and Security · Computer Science 2026-03-20 Md Takrim Ul Alam , Akif Islam , Mohd Ruhul Ameen , Abu Saleh Musa Miah , Jungpil Shin

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers)…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Hangtao Zhang , Yichen Wang , Shihui Yan , Chenyu Zhu , Ziqi Zhou , Linshan Hou , Shengshan Hu , Minghui Li , Yanjun Zhang , Leo Yu Zhang

Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintaining normal performance on clean samples. Among these,…

Cryptography and Security · Computer Science 2025-08-06 Yangxu Yin , Honglong Chen , Yudong Gao , Peng Sun , Liantao Wu , Zhe Li , Weifeng Liu

Persistent Fault Attack (PFA) is a recently proposed Fault Attack (FA) method in CHES 2018. It is able to recover full AES secret key in the Single-Byte-Fault scenario. It is demonstrated that classical FA countermeasures, such as Dual…

Cryptography and Security · Computer Science 2025-12-15 Yukun Cheng , Mengce Zheng , Fan Huang , Jiajia Zhang , Honggang Hu , Nenghai Yu

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

Computation and Language · Computer Science 2024-05-21 Xuanli He , Qiongkai Xu , Jun Wang , Benjamin I. P. Rubinstein , Trevor Cohn

Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet underexplored challenge arises when such backdoors are…

Computation and Language · Computer Science 2025-10-01 Yao Tong , Weijun Li , Xuanli He , Haolan Zhan , Qiongkai Xu

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Proximal causal inference (PCI) is a recently proposed framework to identify and estimate the causal effect of an exposure on an outcome in the presence of hidden confounders, using observed proxies. Specifically, PCI relies on two types of…

Methodology · Statistics 2025-07-29 Prabrisha Rakshit , Xu Shi , Eric Tchetgen Tchetgen

Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the…

Cryptography and Security · Computer Science 2025-02-05 Zihan Guan , Mengxuan Hu , Sheng Li , Anil Vullikanti

Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies. Proxies, which are class-representative points in an embedding space, receive updates based on proxy-sample similarities…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Aoyu Li , Ikuro Sato , Kohta Ishikawa , Rei Kawakami , Rio Yokota

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Cryptography and Security · Computer Science 2026-05-12 Dennis Jacob , Emad Alghamdi , Zhanhao Hu , Basel Alomair , David Wagner

Feature selection is a critical task in machine learning and statistics. However, existing feature selection methods either (i) rely on parametric methods such as linear or generalized linear models, (ii) lack theoretical false discovery…

Machine Learning · Statistics 2025-07-18 Omar Melikechi , David B. Dunson , Jeffrey W. Miller

Due to the growing privacy concerns, decentralization emerges rapidly in personalized services, especially recommendation. Also, recent studies have shown that centralized models are vulnerable to poisoning attacks, compromising their…

Information Retrieval · Computer Science 2021-10-22 Shijie Zhang , Hongzhi Yin , Tong Chen , Zi Huang , Quoc Viet Hung Nguyen , Lizhen Cui

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…

Cryptography and Security · Computer Science 2022-06-13 Nan Luo , Yuanzhang Li , Yajie Wang , Shangbo Wu , Yu-an Tan , Quanxin Zhang

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Computation and Language · Computer Science 2026-05-15 Lin Zheng , Xinyu Li , Qian Liu , Xiachong Feng , Lingpeng Kong

Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing…

Machine Learning · Computer Science 2024-08-15 Kiran Purohit , Soumi Das , Sourangshu Bhattacharya , Santu Rana

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…

Artificial Intelligence · Computer Science 2025-08-22 Zhixiang Guo , Siyuan Liang , Aishan Liu , Dacheng Tao