A step-by-step multimodal 'chain of attack' improves the transferability of targeted adversarial images against open vision-language models, with a new LLM-judged success metric.
Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and generalization; 2) detailed evaluations framework; 3) motivation-driven attack categorizations; and 4) an integrated perspective on both traditional and LVLM attacks. This article addresses these gaps by offering a thorough summary of traditional and LVLM adversarial attacks, emphasizing their connections and distinctions, and providing actionable insights for future research.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
A step-by-step multimodal 'chain of attack' improves the transferability of targeted adversarial images against open vision-language models, with a new LLM-judged success metric.