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
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
Peng Cheng, Yuwei Wang, Peng Huang, Zhongjie Ba, Xiaodong Lin, Feng Lin, Li Lu, Kui Ren
Joint Universal Adversarial Perturbations with Interpretations
Liang-bo Ning, Zeyu Dai, Wenqi Fan, Jingran Su, Chao Pan, Luning Wang, Qing Li
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
Weijie Zheng, Xingjun Ma, Hanxun Huang, Zuxuan Wu, Yu-Gang Jiang
CERT-ED: Certifiably Robust Text Classification for Edit Distance
Zhuoqun Huang, Neil G Marchant, Olga Ohrimenko, Benjamin I. P. Rubinstein
Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks
Angona Biswas, MD Abdullah Al Nasim, Kishor Datta Gupta, Roy George, Abdur Rashid
ADBM: Adversarial diffusion bridge model for reliable adversarial purification
Xiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li, Yining Liu, Yingzhe He, Jie Shi, Xiaolin Hu
AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning
Maisha Binte Rashid, Pablo Rivas
Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon
FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon
Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspective
Bowen Peng, Li Liu, Tianpeng Liu, Zhen Liu, Yongxiang Liu
On Feasibility of Intent Obfuscating Attacks
Zhaobin Li, Patrick Shafto
Towards Robust Vision Transformer via Masked Adaptive Ensemble
Fudong Lin, Jiadong Lou, Xu Yuan, Nian-Feng Tzeng
Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong, Xinli Shi, Yuan Yan Tang, Dacheng Tao