AROW21
* *AROW: Adversarial Robustness in the Real World
* AdvFoolGen: Creating Persistent Troubles for Deep Classifiers
* Can Optical Trojans Assist Adversarial Perturbations?
* Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
* Countering Adversarial Examples: Combining Input Transformation and Noisy Training
* Detecting and Segmenting Adversarial Graphics Patterns from Images
* Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Single-Source Domain Generalization
* Enhancing Adversarial Robustness via Test-Time Transformation Ensembling
* Evasion Attack STeganography: Turning Vulnerability Of Machine Learning To Adversarial Attacks Into A Real-world Application
* Hierarchical Assessment of Adversarial Severity, A
* Impact of Colour on Robustness of Deep Neural Networks
* On Adversarial Robustness: A Neural Architecture Search perspective
* On the Effect of Pruning on Adversarial Robustness
* Optical Adversarial Attack
* Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?
* Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
* Trojan Signatures in DNN Weights
17 for AROW21
AROW23
* *AROW: Adversarial Robustness in the Real World
* Adversarial Examples with Specular Highlights
* Black-Box Attacks on Image Activity Prediction and its Natural Language Explanations
* Classification robustness to common optical aberrations
* Defense-Prefix for Preventing Typographic Attacks on CLIP
* Fair Robust Active Learning by Joint Inconsistency
* IPCert: Provably Robust Intellectual Property Protection for Machine Learning
* OMG-Attack: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
* On the Adversarial Robustness of Multi-Modal Foundation Models
* On the unreasonable vulnerability of transformers for image restoration - and an easy fix
* PRAT: PRofiling Adversarial aTtacks
* Semantically Enhanced Scene Captions with Physical and Weather Condition Changes
* Targeted Adversarial Attacks on Generalizable Neural Radiance Fields
13 for AROW23