English
Related papers

Related papers: EigenShield: Causal Subspace Filtering via Random …

200 papers

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Youcheng Huang , Fengbin Zhu , Jingkun Tang , Pan Zhou , Wenqiang Lei , Jiancheng Lv , Tat-Seng Chua

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Computation and Language · Computer Science 2022-08-23 Jiayi Wang , Rongzhou Bao , Zhuosheng Zhang , Hai Zhao

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Artificial Intelligence · Computer Science 2023-10-31 Leo Schwinn , David Dobre , Stephan Günnemann , Gauthier Gidel

This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework grounded in Spectral Geometry and Random Matrix Theory (RMT). As deep networks and large…

Machine Learning · Computer Science 2026-02-27 Davide Ettori

Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Francesco Villani , Igor Maljkovic , Dario Lazzaro , Angelo Sotgiu , Antonio Emanuele Cinà , Fabio Roli

We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. Based on the idea of…

Machine Learning · Computer Science 2019-09-16 Chaomin Shen , Yaxin Peng , Guixu Zhang , Jinsong Fan

Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models (VLSMs) is still under-explored, especially for medical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Anjila Budathoki , Manish Dhakal

Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold…

Computation and Language · Computer Science 2022-11-08 Dang Minh Nguyen , Luu Anh Tuan

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…

Computation and Language · Computer Science 2021-06-01 Rongzhou Bao , Jiayi Wang , Hai Zhao

Despite their tremendous success in modelling high-dimensional data manifolds, deep neural networks suffer from the threat of adversarial attacks - Existence of perceptually valid input-like samples obtained through careful perturbation…

Computer Vision and Pattern Recognition · Computer Science 2019-09-09 Vinay Kyatham , Mayank Mishra , Tarun Kumar Yadav , Deepak Mishra , Prathosh AP

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Cryptography and Security · Computer Science 2025-01-14 Kaiyi Pang , Tao Qi , Chuhan Wu , Minhao Bai , Minghu Jiang , Yongfeng Huang

Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Junhao Dong , Yifei Zhang , Hao Zhu , Yew-Soon Ong , Piotr Koniusz

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Nadav Kadvil , Malak Fares , Ayellet Tal

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Computation and Language · Computer Science 2020-06-15 Zhaoyang Wang , Hongtao Wang

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Computation and Language · Computer Science 2024-03-19 Javad Rafiei Asl , Prajwal Panzade , Eduardo Blanco , Daniel Takabi , Zhipeng Cai

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

Machine Learning · Computer Science 2023-10-03 Quang H. Nguyen , Yingjie Lao , Tung Pham , Kok-Seng Wong , Khoa D. Doan

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Samar Fares , Klea Ziu , Toluwani Aremu , Nikita Durasov , Martin Takáč , Pascal Fua , Ivan Laptev , Karthik Nandakumar

Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Xinwei Liu , Xiaojun Jia , Yuan Xun , Simeng Qin , Xiaochun Cao

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Xiaowei Fu , Lei Zhang
‹ Prev 1 2 3 10 Next ›