Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs
cs.AI
Submitted: 2026-05-07
Updated: 2026-11-08
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
- VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
- Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Large Language Models: A Survey
- Kimi K2.5: Visual Agentic Intelligence
- Qwen3 Technical Report
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
- VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents