AML23
* *Workshop of Adversarial Machine Learning on Computer Vision: Art of Robustness
* Adversarial Defense in Aerial Detection
* Certified Adversarial Robustness Within Multiple Perturbation Bounds
* Deep Convolutional Sparse Coding Networks for Interpretable Image Fusion
* Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
* Exploring Diversified Adversarial Robustness in Neural Networks via Robust Mode Connectivity
* Extended Study of Human-like Behavior under Adversarial Training, An
* Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness
* How many dimensions are required to find an adversarial example?
* Implications of Solution Patterns on Adversarial Robustness
* Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
* Pilot Study of Query-Free Adversarial Attack against Stable Diffusion, A
* Robustness with Query-efficient Adversarial Attack using Reinforcement Learning
* Universal Watermark Vaccine: Universal Adversarial Perturbations for Watermark Protection
14 for AML23
AML24
* *Adversarial Machine Learning on Computer Vision: Robustness of Foundation Models
* Benchmarking Robustness in Neural Radiance Fields
* Enhancing Targeted Attack Transferability via Diversified Weight Pruning
* Enhancing the Transferability of Adversarial Attacks with Stealth Preservation
* Large Language Models in Wargaming: Methodology, Application, and Robustness
* Learning to Schedule Resistant to Adversarial Attacks in Diffusion Probabilistic Models Under the Threat of Lipschitz Singularities
* Multimodal Attack Detection for Action Recognition Models
* Red-Teaming Segment Anything Model
* Sharpness-Aware Optimization for Real-World Adversarial Attacks for Diverse Compute Platforms with Enhanced Transferability
9 for AML24
AML25
* *Workshop of Adversarial Machine Learning on Computer Vision: Foundation Models + X
* Attacking Attention of Foundation Models Disrupts Downstream Tasks
* Attention-Aware Temporal Adversarial Shadows on Traffic Sign Sequences
* Defending Against Frequency-Based Attacks with Diffusion Models
* EL-Attack: Explicit and Latent Space Hybrid Optimization based General and Effective Attack for Autonomous Driving Trajectory Prediction
* FullCycle: Full Stage Adversarial Attack for Reinforcement Learning Robustness Evaluation
* Probing Vulnerabilities of Vision-Lidar Based Autonomous Driving Systems
* Task-Agnostic Attacks Against Vision Foundation Models
* Towards Evaluating the Robustness of Visual State Space Models
* Trustworthy Multi-UAV Collaboration: A Self-Supervised Framework for Explainable and Adversarially Robust Decision-Making
10 for AML25