English
Related papers

Related papers: Show Me Your Code! Kill Code Poisoning: A Lightwei…

200 papers

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

Machine Learning · Computer Science 2021-03-31 Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Jihun Hamm

Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers…

Cryptography and Security · Computer Science 2021-01-12 Giorgio Severi , Jim Meyer , Scott Coull , Alina Oprea

Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model. Existing defenses for backdoor…

Cryptography and Security · Computer Science 2024-05-21 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer's codebase. While…

Cryptography and Security · Computer Science 2024-10-30 Amit Finkman Noah , Avishag Shapira , Eden Bar Kochva , Inbar Maimon , Dudu Mimran , Yuval Elovici , Asaf Shabtai

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

Backdoor attack is a common threat to deep neural networks. During testing, samples embedded with a backdoor trigger will be misclassified as an adversarial target by a backdoored model, while samples without the backdoor trigger will be…

Machine Learning · Computer Science 2024-01-05 Zhen Xiang , Zidi Xiong , Bo Li

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

Cryptography and Security · Computer Science 2025-08-05 Nilufer Gulciftci , M. Emre Gursoy

With the popularity of Android growing exponentially, the amount of malware has significantly exploded. It is arguably one of the most viral problems on mobile platforms. Recently, various approaches have been introduced to detect Android…

Cryptography and Security · Computer Science 2022-01-25 Peng Xu

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…

Cryptography and Security · Computer Science 2024-11-13 Yulong Yang , Haoran Fan , Chenhao Lin , Qian Li , Zhengyu Zhao , Chao Shen , Xiaohong Guan

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…

Artificial Intelligence · Computer Science 2023-03-14 Zaixi Zhang , Qi Liu , Zhicai Wang , Zepu Lu , Qingyong Hu

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…

Machine Learning · Computer Science 2025-02-11 Hanxun Huang , Sarah Erfani , Yige Li , Xingjun Ma , James Bailey

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the…

Cryptography and Security · Computer Science 2021-12-03 Jinyuan Jia , Yupei Liu , Xiaoyu Cao , Neil Zhenqiang Gong

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

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make…

Cryptography and Security · Computer Science 2021-03-25 Yinpeng Dong , Xiao Yang , Zhijie Deng , Tianyu Pang , Zihao Xiao , Hang Su , Jun Zhu

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…

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

Machine Learning · Computer Science 2020-08-14 Neehar Peri , Neal Gupta , W. Ronny Huang , Liam Fowl , Chen Zhu , Soheil Feizi , Tom Goldstein , John P. Dickerson

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen

Mobile agents powered by vision-language models (VLMs) are increasingly adopted for tasks such as UI automation and camera-based assistance. These agents are typically fine-tuned using small-scale, user-collected data, making them…

Cryptography and Security · Computer Science 2025-09-08 Xuan Wang , Siyuan Liang , Zhe Liu , Yi Yu , Aishan Liu , Yuliang Lu , Xitong Gao , Ee-Chien Chang

With the advancement of Large Language Models (LLMs), significant progress has been made in code generation, enabling LLMs to transform natural language into programming code. These Code LLMs have been widely accepted by massive users and…

Cryptography and Security · Computer Science 2023-12-14 Fangzhou Wu , Xiaogeng Liu , Chaowei Xiao
‹ Prev 1 4 5 6 7 8 10 Next ›