English
Related papers

Related papers: Localization then Neutralization: Gradient-guided …

200 papers

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Xiaojun Jia , Yong Zhang , Baoyuan Wu , Jue Wang , Xiaochun Cao

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each…

Machine Learning · Computer Science 2019-03-27 Yuchen Zhang , Percy Liang

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are…

Machine Learning · Computer Science 2020-03-18 Leo Schwinn , René Raab , Björn Eskofier

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Cryptography and Security · Computer Science 2024-10-14 Xiaopei Zhu , Peiyang Xu , Guanning Zeng , Yingpeng Dong , Xiaolin Hu

Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed…

Machine Learning · Computer Science 2025-01-31 Minh Vu , Geigh Zollicoffer , Huy Mai , Ben Nebgen , Boian Alexandrov , Manish Bhattarai

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…

Computer Vision and Pattern Recognition · Computer Science 2018-06-01 Avishek Joey Bose , Parham Aarabi

Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoroughly examined. We…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xuanming Cui , Alejandro Aparcedo , Young Kyun Jang , Ser-Nam Lim

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma…

Machine Learning · Computer Science 2025-11-04 Zenghao Niu , Weicheng Xie , Siyang Song , Zitong Yu , Feng Liu , Linlin Shen

Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via adversarial prompts. Among existing approaches, the Greedy…

Machine Learning · Computer Science 2026-05-20 Xiao Li , Wei Zhang , Zhuhong Li , Qiongxiu Li , Shei PernChua , BingZe Lee , Jinghao Cui , Yifan Huang , Xiaolin Hu

Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for the corresponding subset of known attacks. Yet, this…

Cryptography and Security · Computer Science 2020-03-02 Sanghyun Hong , Varun Chandrasekaran , Yiğitcan Kaya , Tudor Dumitraş , Nicolas Papernot

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…

Cryptography and Security · Computer Science 2025-09-19 Gustavo Sandoval , Denys Fenchenko , Junyao Chen

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Haibo Zhang , Zhihua Yao , Kouichi Sakurai

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Levente Halmosi , Mark Jelasity

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mengqi He , Xinyu Tian , Xin Shen , Jinhong Ni , Shu Zou , Zhaoyuan Yang , Jing Zhang

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

Cryptography and Security · Computer Science 2020-06-02 Inken Hagestedt , Michael Backes , Andreas Bulling

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

State-of-the-art adversarial attacks are aimed at neural network classifiers. By default, neural networks use gradient descent to minimize their loss function. The gradient of a classifier's loss function is used by gradient-based…

Machine Learning · Computer Science 2020-02-05 Blerta Lindqvist , Rauf Izmailov