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

February 25, 2024

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
Zhiying Jiang, Xingyuan Li, Jinyuan Liu, Xin Fan, Risheng Liu
Adversarial Attack Adversarial Perturbation Adaptive Learning Attack Performance Image Stitching Adaptive Adversarial Training

February 24, 2024

February 23, 2024

February 22, 2024

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu
Adversarial Attack Adversarial Robustness Complex Reasoning Chain of Thought Multimodal LLM Adversarial Image

February 21, 2024

February 19, 2024

February 18, 2024

The Effectiveness of Random Forgetting for Robust Generalization
Vijaya Raghavan T Ramkumar, Bahram Zonooz, Elahe Arani
Adversarial Attack Adversarial Training Anti Forgetting Robust Generalization Adversarial Method Robust Overfitting

February 17, 2024

Maintaining Adversarial Robustness in Continuous Learning
Xiaolei Ru, Xiaowei Cao, Zijia Liu, Jack Murdoch Moore, Xin-Ya Zhang, Xia Zhu, Wenjia Wei, Gang Yan
Adversarial Attack Adversarial Robustness Continuous Learning General Robustness Robust Continual Learning

February 16, 2024

February 15, 2024

A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents
Lingbo Mo, Zeyi Liao, Boyuan Zheng, Yu Su, Chaowei Xiao, Huan Sun
Adversarial Attack Language Agent Attack Strategy

Adversarial Attack

Papers

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks

RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation

Optimal Zero-Shot Detector for Multi-Armed Attacks

Distilling Adversarial Robustness Using Heterogeneous Teachers

A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image

Coercing LLMs to do and reveal (almost) anything

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

An Adversarial Approach to Evaluating the Robustness of Event Identification Models

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Attacks on Node Attributes in Graph Neural Networks

Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training

AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization

Self-Guided Robust Graph Structure Refinement

The Effectiveness of Random Forgetting for Robust Generalization

Maintaining Adversarial Robustness in Continuous Learning

DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation

Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks

A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents