Adversarial Example
Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.
Papers
Improving Robustness Estimates in Natural Language Explainable AI though Synonymity Weighted Similarity Measures
Christopher Burger
AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
Teng Li, Xingjun Ma, Yu-Gang Jiang
Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs
Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo, Xi Xiao, Bo Han, Yongjie Yin, Feng Zheng
Towards Adversarially Robust Deep Metric Learning
Xiaopeng Ke
Boosting Adversarial Transferability with Spatial Adversarial Alignment
Zhaoyu Chen, Haijing Guo, Kaixun Jiang, Jiyuan Fu, Xinyu Zhou, Dingkang Yang, Hao Tang, Bo Li, Wenqiang Zhang
Robust image classification with multi-modal large language models
Francesco Villani, Igor Maljkovic, Dario Lazzaro, Angelo Sotgiu, Antonio Emanuele Cinà, Fabio Roli
Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images
Yasamin Medghalchi, Moein Heidari, Clayton Allard, Leonid Sigal, Ilker Hacihaliloglu