Adversarial smuggling attacks encode harmful content into human-readable visuals that evade MLLM detection, achieving over 90% attack success rates on models like GPT-5 and Qwen3-VL via the new SmuggleBench benchmark.
Visual- roleplay: Universal jailbreak attack on multimodal large language mod- els via role-playing image character
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 4polarities
background 4representative citing papers
CAVI framework uses character-guided token pruning, orthogonal feature modulation, and modality-adaptive role steering to resolve modality-role interference in multimodal RPAs.
Precise Shield identifies safety neurons in VLLMs via activation contrasts and aligns only them with gradient masking, boosting safety, preserving generalization, and enabling zero-shot cross-lingual and cross-modal transfer.
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
RedDiffuser is a reinforced diffusion framework that generates adversarial visual contexts to audit and expose widespread multimodal safety failures in VLMs, increasing unsafe response rates by up to 10.69% on LLaVA with transfer to other models.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
citing papers explorer
-
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
Adversarial smuggling attacks encode harmful content into human-readable visuals that evade MLLM detection, achieving over 90% attack success rates on models like GPT-5 and Qwen3-VL via the new SmuggleBench benchmark.
-
Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
CAVI framework uses character-guided token pruning, orthogonal feature modulation, and modality-adaptive role steering to resolve modality-role interference in multimodal RPAs.
-
Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance
Precise Shield identifies safety neurons in VLLMs via activation contrasts and aligns only them with gradient masking, boosting safety, preserving generalization, and enabling zero-shot cross-lingual and cross-modal transfer.
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
-
RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
RedDiffuser is a reinforced diffusion framework that generates adversarial visual contexts to audit and expose widespread multimodal safety failures in VLMs, increasing unsafe response rates by up to 10.69% on LLaVA with transfer to other models.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.