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 28, 2023

November 27, 2023

November 24, 2023

November 23, 2023

November 22, 2023

November 21, 2023

Attacking Motion Planners Using Adversarial Perception Errors
Jonathan Sadeghi, Nicholas A. Lord, John Redford, Romain Mueller
Adversarial Attack Autonomous Driving Perceptual Quality Motion Planner Perception Error Perceptual Fidelity

November 20, 2023

November 19, 2023

November 18, 2023

Improving Adversarial Transferability by Stable Diffusion
Jiayang Liu, Siyu Zhu, Siyuan Liang, Jie Zhang, Han Fang, Weiming Zhang, Ee-Chien Chang
Adversarial Attack Adversarial Example Stable Diffusion Adversarial Transferability Diffusion Attack

Adversarial Attack

Papers

Generation of Games for Opponent Model Differentiation

On the Robustness of Decision-Focused Learning

Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights

RetouchUAA: Unconstrained Adversarial Attack via Image Retouching

Instruct2Attack: Language-Guided Semantic Adversarial Attacks

Trainwreck: A damaging adversarial attack on image classifiers

Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models

When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence

Security and Privacy Challenges in Deep Learning Models

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization

Hard Label Black Box Node Injection Attack on Graph Neural Networks

Attacking Motion Planners Using Adversarial Perception Errors

BrainWash: A Poisoning Attack to Forget in Continual Learning

Generating Valid and Natural Adversarial Examples with Large Language Models

AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systems

ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches

Adversarial Prompt Tuning for Vision-Language Models

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies

Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications

Improving Adversarial Transferability by Stable Diffusion