English
Related papers

Related papers: A Provable Energy-Guided Test-Time Defense Boostin…

200 papers

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Artificial Intelligence · Computer Science 2024-10-11 Tomas Bueno Momcilovic , Beat Buesser , Giulio Zizzo , Mark Purcell , Dian Balta

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Lin Li , Haoyan Guan , Jianing Qiu , Michael Spratling

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

Computation and Language · Computer Science 2021-04-19 Xiang Gao , Yizhe Zhang , Michel Galley , Bill Dolan

Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are…

Machine Learning · Computer Science 2023-10-13 Girik Malik , Dakarai Crowder , Ennio Mingolla

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Kaleab A. Kinfu , René Vidal

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks…

Cryptography and Security · Computer Science 2025-05-05 Jinsheng Pan , Xiaogeng Liu , Chaowei Xiao

Adversarial training is wildly considered as one of the most effective way to defend against adversarial examples. However, existing adversarial training methods consume unbearable time, due to the fact that they need to generate…

Machine Learning · Computer Science 2021-03-10 Yaguan Qian , Qiqi Shao , Tengteng Yao , Bin Wang , Shouling Ji , Shaoning Zeng , Zhaoquan Gu , Wassim Swaileh

Deep neural networks (DNNs) have achieved remarkable performance in many tasks, yet they often behave as opaque black boxes. Explanation-guided learning (EGL) methods steer DNNs using human-provided explanations or supervision on model…

Machine Learning · Computer Science 2026-03-03 Chao Chen , Yanhui Chen , Shanshan Lin , Dongsheng Hong , Shu Wu , Xiangwen Liao , Chuanyi Liu

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches in training robust models against…

Machine Learning · Computer Science 2022-07-20 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dongchen Han , Yining Li , Tianyu Li , Zixuan Cao , Ziming Wang , Jun Song , Yu Cheng , Bo Zheng , Gao Huang

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

Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ye Liu , Yaya Cheng , Lianli Gao , Xianglong Liu , Qilong Zhang , Jingkuan Song

We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Akshay Kulkarni , Tsui-Wei Weng

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Futa Waseda , Saku Sugawara , Isao Echizen

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…

Cryptography and Security · Computer Science 2025-10-27 Jia Deng , Jin Li , Zhenhua Zhao , Shaowei Wang

How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\epsilon$-robust, consume huge resources, they can only achieve small degree of robustness in…

Machine Learning · Computer Science 2018-11-21 Hajime Ono , Tsubasa Takahashi , Kazuya Kakizaki

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yining Li , Dongchen Han , Zeyu Liu , Hanyi Wang , Yulin Wang , Gao Huang

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle…

Machine Learning · Computer Science 2025-06-10 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Xiaojun Jia , Sensen Gao , Simeng Qin , Ke Ma , Xinfeng Li , Yihao Huang , Wei Dong , Yang Liu , Xiaochun Cao

Recent advances in large vision-language models (LVLMs) have showcased their remarkable capabilities across a wide range of multimodal vision-language tasks. However, these models remain vulnerable to visual adversarial attacks, which can…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Yudong Zhang , Ruobing Xie , Yiqing Huang , Jiansheng Chen , Xingwu Sun , Zhanhui Kang , Di Wang , Yu Wang