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

January 4, 2025

January 3, 2025

January 1, 2025

Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines
Xiyang Hu
Adversarial Attack Large Language Attack Success Rate Efficient Engine Market Manipulation

December 30, 2024

Adversarial Attack and Defense for LoRa Device Identification and Authentication via Deep Learning
Yalin E. Sagduyu, Tugba Erpek
Deep Learning Adversarial Attack Identity Verification LoRA Fine Tuning Fast LoRA LoRa Network

December 29, 2024

On Adversarial Robustness of Language Models in Transfer Learning
Bohdan Turbal, Anastasiia Mazur, Jiaxu Zhao, Mykola Pechenizkiy
Language Model Adversarial Attack Native Robustness Transfer Learning Adversarial Robustness

December 28, 2024

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs
Atmane Ayoub Mansour Bahar, Ahmad Samer Wazan
Large Language Model Adversarial Attack Latent Vulnerability Concurrent Validity Common Vulnerability

December 27, 2024

December 26, 2024

December 25, 2024

Adversarial Attack

Papers

Distillation-Enhanced Physical Adversarial Attacks

Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50

Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI

Detecting and Mitigating Adversarial Attacks on Deep Learning-Based MRI Reconstruction Without Any Retraining

Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs

Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs

Towards Adversarially Robust Deep Metric Learning

Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines

Adversarial Attack and Defense for LoRa Device Identification and Authentication via Deep Learning

On Adversarial Robustness of Language Models in Transfer Learning

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs

Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness

Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning

Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field

Bridging Interpretability and Robustness Using LIME-Guided Model Refinement

Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors

Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation

Evaluating the Adversarial Robustness of Detection Transformers