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
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Egor Kovalev, Georgii Bychkov, Khaled Abud, Aleksandr Gushchin, Anna Chistyakova, Sergey Lavrushkin, Dmitriy Vatolin, Anastasia Antsiferova
Few-shot Model Extraction Attacks against Sequential Recommender Systems
Hui Zhang, Fu Liu
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan, Eric Smith, Javier Rando, Yiming Zhang, Kate Plawiak, Zacharie Delpierre Coudert, Kartikeya Upasani, Mahesh Pasupuleti
Prompt-Guided Environmentally Consistent Adversarial Patch
Chaoqun Li, Huanqian Yan, Lifeng Zhou, Tairan Chen, Zhuodong Liu, Hang Su
Adversarial Attacks Using Differentiable Rendering: A Survey
Matthew Hull, Chao Zhang, Zsolt Kira, Duen Horng Chau
Enhancing generalization in high energy physics using white-box adversarial attacks
Franck Rothen, Samuel Klein, Matthew Leigh, Tobias Golling
BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation
Zheng Zhou, Wenquan Feng, Shuchang Lyu, Guangliang Cheng, Xiaowei Huang, Qi Zhao
Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach
Jiyao Li, Mingze Ni, Yongshun Gong, Wei Liu
Can adversarial attacks by large language models be attributed?
Manuel Cebrian, Jan Arne Telle
Chain Association-based Attacking and Shielding Natural Language Processing Systems
Jiacheng Huang, Long Chen
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models
Pete Janowczyk, Linda Laurier, Ave Giulietta, Arlo Octavia, Meade Cleti
Attention Masks Help Adversarial Attacks to Bypass Safety Detectors
Yunfan Shi
Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging
Rui Luo, Jie Bao, Zhixin Zhou, Chuangyin Dang
Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta
Region-Guided Attack on the Segment Anything Model (SAM)
Xiaoliang Liu, Furao Shen, Jian Zhao
Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning
Jinyin Chen, Wenbo Mu, Luxin Zhang, Guohan Huang, Haibin Zheng, Yao Cheng
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
Jason Vega, Junsheng Huang, Gaokai Zhang, Hangoo Kang, Minjia Zhang, Gagandeep Singh