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

November 27, 2024

Fall Leaf Adversarial Attack on Traffic Sign Classification
Anthony Etim, Jakub Szefer
Adversarial Attack Image Classification Sign Classification
An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)
Ted Kwartler, Nataliia Bagan, Ivan Banny, Alan Aqrawi, Arian Abbasi
Adversarial Attack Text to Image Model Text to Text Text Guided Image Step Attack Aggregate Level Indicator
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Qiang Fu, Aishan Liu, Xianglong Liu
Adversarial Attack Autonomous Driving Vision Language Model Legal Autonomy Driving Context Effective Adversarial
Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
Tian Ye, Rajgopal Kannan, Viktor Prasanna
Adversarial Attack Adversarial Example Adversarial Training Interpolation Regime Semi Supervised Adversarial

November 26, 2024

Stealthy Multi-Task Adversarial Attacks
Jiacheng Guo, Tianyun Zhang, Lei Li, Haochen Yang, Hongkai Yu, Minghai Qin
Adversarial Attack Security Related Attack Efficacy
Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey
Hong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, Nhien-An Le-Khac
Timely Survey Adversarial Attack Deep Fake Multi Modality Face Generation Context Impersonation Passive Sensing
Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers
Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné
Adversarial Attack Adversarial Perturbation Adversarial Loss Object Tracker Transformer Tracker
BadScan: An Architectural Backdoor Attack on Visual State Space Models
Om Suhas Deshmukh, Sankalp Nagaonkar, Achyut Mani Tripathi, Ashish Mishra
Adversarial Attack Visual State Space Model
RED: Robust Environmental Design
Jinghan Yang
Adversarial Attack Native Robustness Visual Input Learning Scheme Patch Based Attack

November 25, 2024

Adversarial Attacks for Drift Detection
Fabian Hinder, Valerie Vaquet, Barbara Hammer
Adversarial Attack Concept Drift Adversarial Text Drift Detection Accurate Detection Real Drift
Sparse patches adversarial attacks via extrapolating point-wise information
Yaniv Nemcovsky, Avi Mendelson, Chaim Baskin
Adversarial Attack Adversarial Perturbation Many Sparse Full Information Multi Scale Patch Sparse Adversarial Attack

November 22, 2024

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Language Models
Wanqi Yang, Yanda Li, Meng Fang, Yunchao Wei, Tianyi Zhou, Ling Chen
Language Model Adversarial Attack Evaluation Benchmark Adversarial Audio Audio Attack
Adversarial Prompt Distillation for Vision-Language Models
Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun Ma
Adversarial Attack Vision Language Model Adversarial Robustness Pre Trained Vision Language Model Prompt Distillation

November 21, 2024

Learning Fair Robustness via Domain Mixup
Meiyu Zhong, Ravi Tandon
Adversarial Attack Adversarial Training Adversarial Risk Domain Mixup

Adversarial Attack

Papers

Fall Leaf Adversarial Attack on Traffic Sign Classification

An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation

Stealthy Multi-Task Adversarial Attacks

Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey

Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers

BadScan: An Architectural Backdoor Attack on Visual State Space Models

RED: Robust Environmental Design

Adversarial Attacks for Drift Detection

Sparse patches adversarial attacks via extrapolating point-wise information

A Tunable Despeckling Neural Network Stabilized via Diffusion Equation

ExAL: An Exploration Enhanced Adversarial Learning Algorithm

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks

Enhancing the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation

MUNBa: Machine Unlearning via Nash Bargaining

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Language Models

Adversarial Prompt Distillation for Vision-Language Models

Learning Fair Robustness via Domain Mixup