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

March 7, 2024

Fooling Neural Networks for Motion Forecasting via Adversarial Attacks
Edgar Medina, Leyong Loh
Adversarial Attack Human Motion Prediction Motion Forecasting Multivariate Regression Deep Fake Detection

March 5, 2024

March 4, 2024

March 3, 2024

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
Arijit Ghosh Chowdhury, Md Mofijul Islam, Vaibhav Kumar, Faysal Hossain Shezan, Vaibhav Kumar, Vinija Jain, Aman Chadha
Natural Language Processing Adversarial Attack New Attack LLM Safety LLM Attack

March 2, 2024

SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters
Jiahao Cui, Jiale Duan, Binyan Luo, Hang Cao, Wang Guo, Haifeng Li
Adversarial Attack Wavelet Scattering

March 1, 2024

February 29, 2024

February 28, 2024

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
Zhewei Wu, Ruilong Yu, Qihe Liu, Shuying Cheng, Shilin Qiu, Shijie Zhou
Adversarial Attack Adversarial Training Adversarial Perturbation Adversarial Defense Robust Tracking Auxiliary Adversarial

February 27, 2024

February 26, 2024

Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing
Kefu Guo, Fengfan Zhou, Hefei Ling, Ping Li, Hui Liu
Adversarial Attack Adversarial Example Adversarial Perturbation Face Recognition Joint Photographic Expert Group Adversarial Face

February 25, 2024

Adversarial Attack

Papers

Fooling Neural Networks for Motion Forecasting via Adversarial Attacks

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability

Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors

XAI-Based Detection of Adversarial Attacks on Deepfake Detectors

Towards Robust Federated Learning via Logits Calibration on Non-IID Data

Improving the Robustness of Object Detection and Classification AI models against Adversarial Patch Attacks

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models

SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters

Resilience of Entropy Model in Distributed Neural Networks

Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey

Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks

Black-box Adversarial Attacks Against Image Quality Assessment Models

Extreme Miscalibration and the Illusion of Adversarial Robustness

Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing

ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings

Adversarial-Robust Transfer Learning for Medical Imaging via Domain Assimilation