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

September 10, 2023

September 9, 2023

September 8, 2023

September 7, 2023

September 6, 2023

SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series
Chang George Dong, Liangwei Nathan Zheng, Weitong Chen, Wei Emma Zhang, Lin Yue
Adversarial Attack Time Series Time Series Classification Adversarial Method Swap Distance Minimization Second Ranked Logits

September 5, 2023

September 3, 2023

Adversarial Attack

Papers

Outlier Robust Adversarial Training

DAD++: Improved Data-free Test Time Adversarial Defense

Machine Translation Models Stand Strong in the Face of Adversarial Attacks

Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing

Exploring Robust Features for Improving Adversarial Robustness

Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse

Adversarial attacks on hybrid classical-quantum Deep Learning models for Histopathological Cancer Detection

Adversarially Robust Deep Learning with Optimal-Transport-Regularized Divergences

DiffDefense: Defending against Adversarial Attacks via Diffusion Models

How adversarial attacks can disrupt seemingly stable accurate classifiers

SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series

Adaptive Adversarial Training Does Not Increase Recourse Costs

RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems

MathAttack: Attacking Large Language Models Towards Math Solving Ability

Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration

Toward Defensive Letter Design

Robust and Efficient Interference Neural Networks for Defending Against Adversarial Attacks in ImageNet

Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection

Dual Adversarial Resilience for Collaborating Robust Underwater Image Enhancement and Perception

Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework