English
Related papers

Related papers: AdaptGuard: Defending Against Universal Attacks fo…

200 papers

We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.…

Machine Learning · Computer Science 2021-10-05 Marcus de Carvalho , Mahardhika Pratama , Jie Zhang , Edward Yapp

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…

Cryptography and Security · Computer Science 2023-08-30 Zhou Yang , Bowen Xu , Jie M. Zhang , Hong Jin Kang , Jieke Shi , Junda He , David Lo

Deep Neural Networks have been found vulnerable re-cently. A kind of well-designed inputs, which called adver-sarial examples, can lead the networks to make incorrectpredictions. Depending on the different scenarios, goalsand capabilities,…

Machine Learning · Computer Science 2022-06-14 Junde Wu , Rao Fu

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and…

Cryptography and Security · Computer Science 2018-01-08 Jamie Hayes , George Danezis

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Machine Learning · Computer Science 2024-07-18 Avery Ma , Amir-massoud Farahmand , Yangchen Pan , Philip Torr , Jindong Gu

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Machine Learning · Computer Science 2024-03-12 Xiaoyang Wang , Dimitrios Dimitriadis , Sanmi Koyejo , Shruti Tople

Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects…

Cryptography and Security · Computer Science 2025-03-03 Yuning Han , Bingyin Zhao , Rui Chu , Feng Luo , Biplab Sikdar , Yingjie Lao

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Machine Learning · Computer Science 2025-09-29 Sujeevan Aseervatham , Achraf Kerzazi , Younès Bennani

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers…

Machine Learning · Computer Science 2026-03-03 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

Machine Learning · Computer Science 2022-06-15 Kaustubh Sridhar , Souradeep Dutta , Ramneet Kaur , James Weimer , Oleg Sokolsky , Insup Lee

We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from the source to the target domain, coupled with the…

Machine Learning · Computer Science 2022-10-20 Mengmeng Jing , Xiantong Zhen , Jingjing Li , Cees G. M. Snoek

Today, the security of many domains rely on the use of Machine Learning to detect threats, identify vulnerabilities, and safeguard systems from attacks. Recently, transformer architectures have improved the state-of-the-art performance on a…

Cryptography and Security · Computer Science 2023-10-19 Kunyang Li , Kyle Domico , Jean-Charles Noirot Ferrand , Patrick McDaniel

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Khoi Nguyen Tiet Nguyen , Wenyu Zhang , Kangkang Lu , Yuhuan Wu , Xingjian Zheng , Hui Li Tan , Liangli Zhen

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

Machine Learning · Computer Science 2026-04-07 Ganghua Wang , Yuhong Yang , Jie Ding

We introduce the concept of "universal password model" -- a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achieve this, the model does not need to access any plaintext…

Cryptography and Security · Computer Science 2024-03-14 Dario Pasquini , Giuseppe Ateniese , Carmela Troncoso

Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains. When the source domains are…

Machine Learning · Computer Science 2022-11-16 Serban Stan , Mohammad Rostami

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…

Machine Learning · Computer Science 2025-08-26 Quanwei Wu , Jun Guo , Wei Wang , Yi Wang

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at…

Machine Learning · Computer Science 2020-10-26 Florian Tramer , Nicholas Carlini , Wieland Brendel , Aleksander Madry

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Cryptography and Security · Computer Science 2025-09-23 Brendan Murphy , Dillon Bowen , Shahrad Mohammadzadeh , Tom Tseng , Julius Broomfield , Adam Gleave , Kellin Pelrine