Copertina

Alignment and Adversarial Robustness: Are More Human-Like Models More Secure?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hoak, Blaine, Li, Kunyang, McDaniel, Patrick
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Explorations in Texture Learning
di: Hoak, Blaine, et al.
Pubblicazione: (2024)

On Synthetic Texture Datasets: Challenges, Creation, and Curation
di: Hoak, Blaine, et al.
Pubblicazione: (2024)

Err on the Side of Texture: Texture Bias on Real Data
di: Hoak, Blaine, et al.
Pubblicazione: (2024)

On the Robustness Tradeoff in Fine-Tuning
di: Li, Kunyang, et al.
Pubblicazione: (2025)

Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises
di: Choi, Minkyu, et al.
Pubblicazione: (2022)

Robust Lane Detection with Wavelet-Enhanced Context Modeling and Adaptive Sampling
di: Li, Kunyang, et al.
Pubblicazione: (2025)

Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
di: Lu, Zitong, et al.
Pubblicazione: (2024)

Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
di: Kim, Kiyoon, et al.
Pubblicazione: (2024)

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
di: Xue, Haotian, et al.
Pubblicazione: (2024)

More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment
di: Xie, Jun, et al.
Pubblicazione: (2025)

Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
di: Wang, Yanyun, et al.
Pubblicazione: (2026)

RESBev: Making BEV Perception More Robust
di: Zhuo, Lifeng, et al.
Pubblicazione: (2026)

Lane2Seq: Towards Unified Lane Detection via Sequence Generation
di: Zhou, Kunyang
Pubblicazione: (2024)

DiffusionLane: Diffusion Model for Lane Detection
di: Zhou, Kunyang, et al.
Pubblicazione: (2025)

More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV
di: Ye, Kai, et al.
Pubblicazione: (2025)

Adapted Center and Scale Prediction: More Stable and More Accurate
di: Wang, Wenhao, et al.
Pubblicazione: (2020)

No More Sibling Rivalry: Debiasing Human-Object Interaction Detection
di: Yang, Bin, et al.
Pubblicazione: (2025)

Exploring More from Multiple Gait Modalities for Human Identification
di: Jin, Dongyang, et al.
Pubblicazione: (2024)

Unlearning the Noisy Correspondence Makes CLIP More Robust
di: Han, Haochen, et al.
Pubblicazione: (2025)

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
di: Gorgun, Ada, et al.
Pubblicazione: (2025)

ViUniT: Visual Unit Tests for More Robust Visual Programming
di: Panagopoulou, Artemis, et al.
Pubblicazione: (2024)

One-for-More: Continual Diffusion Model for Anomaly Detection
di: Li, Xiaofan, et al.
Pubblicazione: (2025)

Hypergraph Vision Transformers: Images are More than Nodes, More than Edges
di: Fixelle, Joshua
Pubblicazione: (2025)

The More You See in 2D, the More You Perceive in 3D
di: Han, Xinyang, et al.
Pubblicazione: (2024)

More Images, More Problems? A Controlled Analysis of VLM Failure Modes
di: Das, Anurag, et al.
Pubblicazione: (2026)

The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment
di: Koutoupis, Stefanos, et al.
Pubblicazione: (2025)

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
di: Zhang, Kejia, et al.
Pubblicazione: (2024)

Learning More by Seeing Less: Structure First Learning for Efficient, Transferable, and Human-Aligned Vision
di: Li, Tianqin, et al.
Pubblicazione: (2025)

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
di: Wang, Xiangchen, et al.
Pubblicazione: (2025)

More Pictures Say More: Visual Intersection Network for Open Set Object Detection
di: Dong, Bingcheng, et al.
Pubblicazione: (2024)

Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
di: Zeng, Fanhu, et al.
Pubblicazione: (2026)

Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability
di: Najafi, Mohammad Hossein, et al.
Pubblicazione: (2025)

AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
di: Xu, Yitao, et al.
Pubblicazione: (2024)

Edge Detectors Can Make Deep Convolutional Neural Networks More Robust
di: Ding, Jin, et al.
Pubblicazione: (2024)

Landscape More Secure Than Portrait? Zooming Into the Directionality of Digital Images With Security Implications
di: Lorch, Benedikt, et al.
Pubblicazione: (2024)

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models
di: Xing, Songlong, et al.
Pubblicazione: (2026)

SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
di: Wu, Xiaodong, et al.
Pubblicazione: (2025)

A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback
di: Khaertdinov, Bulat, et al.
Pubblicazione: (2025)

Shedding More Light on Robust Classifiers under the lens of Energy-based Models
di: Mirza, Mujtaba Hussain, et al.
Pubblicazione: (2024)

Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
di: Hernández-Cámara, Pablo, et al.
Pubblicazione: (2025)