UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
Title resolution pending
3 Pith papers cite this work, alongside 96 external citations. Polarity classification is still indexing.
3
Pith papers citing it
96
external citations · OpenAlex
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 3representative citing papers
Degraded image resolution in MLLMs bypasses safety alignments via cognitive overload, raising jailbreak rates across perturbations.
MemJack achieves 71.48% attack success rate on unmodified COCO val2017 images against Qwen3-VL-Plus by coordinating agents to map visual entities to malicious intents, apply multi-angle camouflage, and filter refusals via iterative nullspace projection while transferring strategies through a shared
citing papers explorer
-
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
-
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
Degraded image resolution in MLLMs bypasses safety alignments via cognitive overload, raising jailbreak rates across perturbations.
-
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
MemJack achieves 71.48% attack success rate on unmodified COCO val2017 images against Qwen3-VL-Plus by coordinating agents to map visual entities to malicious intents, apply multi-angle camouflage, and filter refusals via iterative nullspace projection while transferring strategies through a shared