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
Distributional Adversarial Loss
Saba Ahmadi, Siddharth Bhandari, Avrim Blum, Chen Dan, Prabhav Jain
Graph Neural Network Explanations are Fragile
Jiate Li, Meng Pang, Yun Dong, Jinyuan Jia, Binghui Wang
ZeroPur: Succinct Training-Free Adversarial Purification
Xiuli Bi, Zonglin Yang, Bo Liu, Xiaodong Cun, Chi-Man Pun, Pietro Lio, Bin Xiao
VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise
Zhixun He, Mukesh Singhal
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain
Jun Liu, Jiantao Zhou, Jiandian Zeng, Jinyu Tian, Zheng Li
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
Ethan Rathbun, Christopher Amato, Alina Oprea
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation
Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
Robust Kernel Hypothesis Testing under Data Corruption
Antonin Schrab, Ilmun Kim
Enhancing Adversarial Robustness in SNNs with Sparse Gradients
Yujia Liu, Tong Bu, Jianhao Ding, Zecheng Hao, Tiejun Huang, Zhaofei Yu
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Yipu Chen, Haotian Xue, Yongxin Chen
Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning
Keltin Grimes, Collin Abidi, Cole Frank, Shannon Gallagher
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
Shuyu Cheng, Yibo Miao, Yinpeng Dong, Xiao Yang, Xiao-Shan Gao, Jun Zhu
Verifiably Robust Conformal Prediction
Linus Jeary, Tom Kuipers, Mehran Hosseini, Nicola Paoletti
Leveraging Many-To-Many Relationships for Defending Against Visual-Language Adversarial Attacks
Futa Waseda, Antonio Tejero-de-Pablos