Adversarial Vulnerability

Adversarial vulnerability explores how seemingly minor input manipulations can drastically alter the predictions of machine learning models, particularly deep neural networks (DNNs), including vision transformers (ViTs) and vision-language pre-training (VLP) models. Current research focuses on developing more effective adversarial attacks, evaluating model robustness across various architectures and tasks (e.g., image classification, semantic segmentation, multi-task learning, and LLMs), and designing defenses such as adversarial training and robust proxy learning. Understanding and mitigating adversarial vulnerability is crucial for ensuring the reliability and safety of AI systems deployed in high-stakes applications, from autonomous vehicles to medical diagnosis.

Papers

October 17, 2024

Golyadkin's Torment: Doppelgängers and Adversarial Vulnerability
George I. Kamberov
Adversarial Example Meta Learning Generative Adversarial Adversarial Vulnerability Accuracy Robustness Adversarial Imitation Lookalike Model

October 9, 2024

Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility
Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin
Native Robustness Adversarial Vulnerability Better Robustness Enhanced Robustness Experiential Consequence Batch Norm

October 7, 2024

Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
Dehong Kong, Siyuan Liang, Xiaopeng Zhu, Yuansheng Zhong, Wenqi Ren
Adversarial Attack Full Model Vision Language Adversarial Perturbation Multimodal Learning Adversarial Patch Adversarial Vulnerability Single Simple Patch

September 26, 2024

Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
Supriya Manna, Niladri Sett
Natural Language Processing Adversarial Attack Explainable AI Adversarial Vulnerability Faithfulness Test Adversarial Change

September 19, 2024

VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness
Xuan Cai, Zhiyong Cui, Xuesong Bai, Ruimin Ke, Zhenshu Ma, Haiyang Yu, Yilong Ren
Autonomous Vehicle Adversarial Vulnerability Training Time Attack Adversarial Policy Robust Autonomous Driving Curiosity Driven Learning

August 24, 2024

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
Jiwei Guan, Tianyu Ding, Longbing Cao, Lei Pan, Chen Wang, Xi Zheng
Adversarial Attack Native Robustness Adversarial Robustness Vision Language Adversarial Perturbation Adversarial Vulnerability Multimodal Attack

August 3, 2024

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
Weijie Zheng, Xingjun Ma, Hanxun Huang, Zuxuan Wu, Yu-Gang Jiang
Adversarial Attack Adversarial Example Pre Trained Vision Transformer Adversarial Vulnerability Pre Trained ViT Downstream Model Transfer Based Attack

July 25, 2024

A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
Haonan Zheng, Xinyang Deng, Wen Jiang, Wenrui Li
Full Model Downstream Task Adversarial Image Unimodal Model Adversarial Vulnerability Unified View

July 16, 2024

Enhancing TinyML Security: Study of Adversarial Attack Transferability
Parin Shah, Yuvaraj Govindarajulu, Pavan Kulkarni, Manojkumar Parmar
Adversarial Attack Study Feature TinyML Model Adversarial Vulnerability Embedded System Adversarial Transferability

July 3, 2024

A Geometric Framework for Adversarial Vulnerability in Machine Learning
Brian Bell
Machine Learning Adversarial Attack Adversarial Perturbation Adversarial Vulnerability Domain Adversarial Manifold Hypothesis Geometric Framework

June 26, 2024

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot, Frédéric Precioso, Christian Gagné
Adversarial Attack Native Robustness Adversarial Vulnerability Robust Decision Margin Consistency

June 23, 2024

Towards unlocking the mystery of adversarial fragility of neural networks
Jingchao Gao, Raghu Mudumbai, Xiaodong Wu, Jirong Yi, Catherine Xu, Hui Xie, Weiyu Xu
Neural Network Deep Neural Network Adversarial Robustness Adversarial Vulnerability Mystery Suspense Whodunit

May 24, 2024

Adversarial Attacks on Hidden Tasks in Multi-Task Learning
Yu Zhe, Rei Nagaike, Daiki Nishiyama, Kazuto Fukuchi, Jun Sakuma
Adversarial Attack Multi Task Learning Adversarial Vulnerability Unseen Task

April 29, 2024

Harmonic Machine Learning Models are Robust
Nicholas S. Kersting, Yi Li, Aman Mohanty, Oyindamola Obisesan, Raphael Okochu
Native Robustness High Dimensional Ground Truth Adversarial Vulnerability Noise Robustness Harmonic Potential

April 21, 2024

Fermi-Bose Machine achieves both generalization and adversarial robustness
Mingshan Xie, Yuchen Wang, Haiping Huang
Adversarial Example New Machine Back Propagation Adversarial Vulnerability Hidden Layer Local Contrastive

April 3, 2024

Adversarial Attacks and Dimensionality in Text Classifiers
Nandish Chattopadhyay, Atreya Goswami, Anupam Chattopadhyay
Adversarial Attack Adversarial Example Data Dimensionality Adversarial DEfense Adversarial Vulnerability Text Classifier

March 19, 2024

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
Anjun Hu, Jindong Gu, Francesco Pinto, Konstantinos Kamnitsas, Philip Torr
Adversarial Example Foundation Model Downstream Task Flawed Foundation Adversarial Vulnerability Adversarial Defense

March 6, 2024

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
Rajdeep Haldar, Yue Xing, Qifan Song
Adversarial Attack Mixed Effect Adversarial Perturbation Adversarial Vulnerability Intrinsic Dimension Manifold Attack

February 21, 2024

Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment
Vyas Raina, Adian Liusie, Mark Gales
Adversarial Robustness Adversarial Vulnerability LLM Based Evaluation Universal Adversarial Zero Shot LLM

February 2, 2024

Delving into Decision-based Black-box Attacks on Semantic Segmentation
Zhaoyu Chen, Zhengyang Shan, Jingwen Chang, Kaixun Jiang, Dingkang Yang, Yiting Cheng, Wenqiang Zhang
Semantic Segmentation Adversarial Robustness Semantic Segmentation Model Adversarial Vulnerability Decision Based