CVPR 2026 Past AgentsSafety & alignmentComputer vision
The 6th Workshop of Adversarial Machine Learning on Computer Vision: Safety of Vision-Language Agents
6thAdvML
- Submission deadline
- Mar 8, 2026, 16:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (10)
Fetched from OpenReview (v2) on 2026-06-10.
-
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
-
ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
-
Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?
-
Evaluating Vulnerabilities in Vision-Language Models: Impact of Behavior-Induced Interference
-
Interpretable Adversarial Prompt Tuning via Semantic Concepts
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
-
Robustness of Vision Foundation Models to Common Perturbations
-
SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
-
SASA: Sequence-Aware Shadow Attacks via Attention Alignment for Traffic Sign Recognition
-
SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement