Research map / Adversarial robustness and security / Attacks on text and graphs
The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
Mauricio Byrd Victorica, Ezzeldin Shereen, György Dán
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a detector for visual adversarial examples against vision-language models based on self-targeted gradient characterization, evaluated against adaptive white-box attacks.
Problem
Visual adversarial examples threaten vision-language models, and existing VLM robustness work often ignores adaptive white-box attacks where the adversary knows the defense.
Approach
Detects adversarial images via a self-targeted gradient characterization of the input against the VLM, aiming to remain effective under adaptive white-box attacks (exact mechanism not stated in the abstract).
Closest papers by meaning
- Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks (CVPR 2025 · similarity 0.89)
- R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning (CVPR 2025 · similarity 0.88)
- Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models (CVPR 2025 · similarity 0.87)
- Visual Adversarial Examples Jailbreak Aligned Large Language Models (AAAI 2024 · similarity 0.87)
- Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models (NeurIPS 2024 · similarity 0.87)
- Attention! Your Vision Language Model Could Be Maliciously Manipulated (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
