Adversarial Attack
Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.
Papers
Detecting Adversarial Data via Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets
Hyekyoung Hwang, Jitae Shin
Revisit, Extend, and Enhance Hessian-Free Influence Functions
Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning
Simon Yu, Jie He, Pasquale Minervini, Jeff Z. Pan
Can Implicit Bias Imply Adversarial Robustness?
Hancheng Min, René Vidal
Efficient Adversarial Training in LLMs with Continuous Attacks
Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Guanlin Li, Kangjie Chen, Shudong Zhang, Jie Zhang, Tianwei Zhang
Large Language Model Sentinel: LLM Agent for Adversarial Purification
Guang Lin, Qibin Zhao
Adversarial Attacks on Hidden Tasks in Multi-Task Learning
Yu Zhe, Rei Nagaike, Daiki Nishiyama, Kazuto Fukuchi, Jun Sakuma
Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark
Huali Ren, Anli Yan, Chong-zhi Gao, Hongyang Yan, Zhenxin Zhang, Jin Li
Overcoming the Challenges of Batch Normalization in Federated Learning
Rachid Guerraoui, Rafael Pinot, Geovani Rizk, John Stephan, François Taiani
SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines
Andrea Ponte, Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Ivan Tesfai Ogbu, Fabio Roli
Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds
Hanwei Zhang, Luo Cheng, Qisong He, Wei Huang, Renjue Li, Ronan Sicre, Xiaowei Huang, Holger Hermanns, Lijun Zhang
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography
Nhat Chung, Sensen Gao, Tuan-Anh Vu, Jie Zhang, Aishan Liu, Yun Lin, Jin Song Dong, Qing Guo
Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization
Daniel Kuelbs, Sanjay Lall, Mert Pilanci
Towards Certification of Uncertainty Calibration under Adversarial Attacks
Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz, Philip H. S. Torr, Adel Bibi
Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers
Shayan Mohajer Hamidi, Linfeng Ye