Navigating the Trade-off: A Synthesis of Defensive Strategies for Zero-Shot Adversarial Robustness in Vision-Language Models

2025-08-07 · Zane Xu, Jason Sun arxiv

This report synthesizes eight seminal papers on the zero-shot adversarial robustness of vision-language models (VLMs) like CLIP. A central challenge in this domain is the inherent trade-off between enhancing adversarial robustness and preserving the model's zero-shot generalization capabilities. We analyze two primary defense paradigms: Adversarial Fine-Tuning (AFT), which modifies model parameters, and Training-Free/Test-Time Defenses, which preserve them. We trace the evolution from alignment-preserving methods (TeCoA) to embedding space re-engineering (LAAT, TIMA), and from input heuristics (AOM, TTC) to latent-space purification (CLIPure). Finally, we identify key challenges and future directions including hybrid defense strategies and adversarial pre-training.

📄 PDF Abstract BibTeX arXiv:2508.05237

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot Generalization Adversarial Robustness

Understanding Humans' Strategies in Maze Solving

2013-07-22 · Min Zhao, Andre G. Marquez

Navigating through a visual maze relies on the strategic use of eye movements to select and identify the route. When navigating the maze, there are trade-offs between exploring to the environment and relying on memory. T…

Error Understanding

Selective Classifier-free Guidance for Zero-shot Text-to-speech

2025-09-24 · John Zheng, Farhad Maleki arxiv

In zero-shot text-to-speech, achieving a balance between fidelity to the target speaker and adherence to text content remains a challenge. While classifier-free guidance (CFG) strategies have shown promising results in i…

Speech Synthesis Image Generation

Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging

2024-11-07 · Rui Luo, Jie Bao, Zhixin Zhou, Chuangyin Dang

Adversarial attacks pose significant threats to the reliability and safety of deep learning models, especially in critical domains such as medical imaging. This paper introduces a novel framework that integrates conforma…

Adversarial Robustness Conformal Prediction Prediction Uncertainty Quantification+1

Adversarial Reinforcement Learning for Offensive and Defensive Agents in a Simulated Zero-Sum Network Environment

2025-10-03 · Abrar Shahid, Ibteeker Mahir Ishum, AKM Tahmidul Haque, M Sohel Rahman 외 arxiv

This paper presents a controlled study of adversarial reinforcement learning in network security through a custom OpenAI Gym environment that models brute-force attacks and reactive defenses on multi-port services. The e…

Reinforcement Learning Transfer Learning OpenAI Gym

The Advantage of Doubling: A Deep Reinforcement Learning Approach to Studying the Double Team in the NBA

2018-03-08 · Jiaxuan Wang, Ian Fox, Jonathan Skaza, Nick Linck 외

During the 2017 NBA playoffs, Celtics coach Brad Stevens was faced with a difficult decision when defending against the Cavaliers: "Do you double and risk giving up easy shots, or stay at home and do the best you can?" I…

Deep Reinforcement Learning Reinforcement Learning