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 10, 2023

Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous
Ziwei Wang, Nabil Aouf, Jose Pizarro, Christophe Honvault
Deep Learning Adversarial Attack Relative Pose Adversarial Detection Rendezvous Problem Autonomous Spacecraft Adversarial Attack Detection Relative Positional

November 8, 2023

November 6, 2023

Can LLMs Follow Simple Rules?
Norman Mu, Sarah Chen, Zifan Wang, Sizhe Chen, David Karamardian, Lulwa Aljeraisy, Basel Alomair, Dan Hendrycks, David Wagner
Large Language Model Adversarial Attack Instruction Following Simple RULE

November 3, 2023

November 2, 2023

Adversary ML Resilience in Autonomous Driving Through Human Centered Perception Mechanisms
Aakriti Shah
Adversarial Attack Autonomous Driving Adversarial Example Sign Classification Human Centric Perception

November 1, 2023

October 31, 2023

October 30, 2023

October 29, 2023

Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors
Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, Xianchao Zhang
Adversarial Attack Gradient Estimation Decision Based

October 28, 2023

Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness
Boya Zhang, Weijian Luo, Zhihua Zhang
Adversarial Attack External Control Inherent Randomness Adversarial Purification Diffusion Purification

October 27, 2023

Understanding and Improving Ensemble Adversarial Defense
Yian Deng, Tingting Mu
Adversarial Attack Human Understanding Adversarial DEfense Adversarial Scenario Ensemble Adversarial

Adversarial Attack

Papers

Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous

Familiarity-Based Open-Set Recognition Under Adversarial Attacks

Be Careful When Evaluating Explanations Regarding Ground Truth

Can LLMs Follow Simple Rules?

The Alignment Problem in Context

Adversarial Attacks on Cooperative Multi-agent Bandits

Adversary ML Resilience in Autonomous Driving Through Human Centered Perception Mechanisms

Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems

Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks

Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

Adversarial Examples in the Physical World: A Survey

Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems

Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations

Exploring Geometry of Blind Spots in Vision Models

Adversarial Attacks and Defenses in Large Language Models: Old and New Threats

Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors

Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness

Understanding and Improving Ensemble Adversarial Defense