Zero Shot Adversarial Robustness

Zero-shot adversarial robustness focuses on improving the resilience of large-scale models, particularly vision-language models like CLIP, to adversarial attacks without requiring retraining on the target task. Current research emphasizes techniques like adversarial prompt learning, contrastive training, and model-guided fine-tuning to enhance robustness while preserving zero-shot generalization capabilities. These methods aim to improve the accuracy and reliability of these models in real-world scenarios where unseen or maliciously perturbed inputs are common. The field's advancements are crucial for building more trustworthy and dependable AI systems across various applications.

Papers

October 29, 2024

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
Lu Yu, Haiyang Zhang, Changsheng Xu
Vision Language Model Adversarial Robustness Attention Network Zero Shot Adversarial Robustness

October 21, 2024

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems
Yihuan Mao, Yipeng Kang, Peilun Li, Ning Zhang, Wei Xu, Chongjie Zhang
Software Defined Consensus Mechanism Byzantine Fault Tolerance Zero Shot Adversarial Robustness Byzantine Failure

May 27, 2024

TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability
Fengji Ma, Li Liu, Hei Victor Cheng
Zero Shot Adversarial Robustness Zero Shot Generalization Zero Shot Adversarial Robustness

March 21, 2024

Few-Shot Adversarial Prompt Learning on Vision-Language Models
Yiwei Zhou, Xiaobo Xia, Zhiwei Lin, Bo Han, Tongliang Liu
Vision Language Model Cross Modal Alignment Adversarial Prompt Prompt Based Few Shot Zero Shot Adversarial Robustness

January 9, 2024

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
Sibo Wang, Jie Zhang, Zheng Yuan, Shiguang Shan
Adversarial Training Zero Shot Generalization Adversarial Fine Tuning Zero Shot Adversarial Robustness

September 8, 2023

Zero-Shot Robustification of Zero-Shot Models
Dyah Adila, Changho Shin, Linrong Cai, Frederic Sala
Language Model Zero Shot Zero Shot Learning Zero Shot Model Zero Shot Baseline Zero Shot Adversarial Robustness

June 20, 2023

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
Jiuding Sun, Chantal Shaib, Byron C. Wallace
Instruction Tuned Model Instruction Fine Tuning Instruction Tuned Language Model Zero Shot Adversarial Robustness Instruction Phrasing

January 30, 2023

Language-Driven Anchors for Zero-Shot Adversarial Robustness
Xiao Li, Wei Zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu
Adversarial Attack Adversarial Training Adversarial Robustness Zero Shot Adversarial Robustness

December 14, 2022

Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
Chengzhi Mao, Scott Geng, Junfeng Yang, Xin Wang, Carl Vondrick
Adversarial Robustness Large Scale Model Imperceptible Adversarial Perturbation Zero Shot Adversarial Robustness

September 14, 2022

Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries
Alexander Cann, Ian Colbert, Ihab Amer
Adversarial Example Adversarial Robustness Adversarial DEfense White Box Feature Transfer Pre Processing Zero Shot Adversarial Robustness

July 14, 2022

Contrastive Adapters for Foundation Model Group Robustness
Michael Zhang, Christopher Ré
Zero Shot Classification Group Robustness Zero Shot Adversarial Robustness

January 26, 2022

How Robust are Discriminatively Trained Zero-Shot Learning Models?
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
Adversarial Attack Zero Shot Learning Learning Model Image Corruption Zero Shot Adversarial Robustness