Cover Image

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Nanxi, Zhao, Zhengyue, Suh, G. Edward, Pavone, Marco, Xiao, Chaowei
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
by: Li, Nanxi, et al.
Published: (2026)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
by: Li, Hao, et al.
Published: (2026)

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
by: Liu, Xiaogeng, et al.
Published: (2026)

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
by: Liu, Qin, et al.
Published: (2025)

ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
by: Zhao, Zhengyue, et al.
Published: (2025)

AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
by: Liu, Xiaogeng, et al.
Published: (2025)

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
by: Li, MingSheng, et al.
Published: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
by: Xiang, Chong, et al.
Published: (2026)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
by: Chen, Jianhao, et al.
Published: (2025)

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
by: Wang, Yu, et al.
Published: (2024)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
by: Yin, Qingyu, et al.
Published: (2025)

PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models
by: Chen, Jiangong, et al.
Published: (2026)

SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
by: Fang, Xianya, et al.
Published: (2026)

Reimagining Safety Alignment with An Image
by: Xia, Yifan, et al.
Published: (2025)

OET: Optimization-based prompt injection Evaluation Toolkit
by: Pan, Jinsheng, et al.
Published: (2025)

RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
by: Wang, Peiran, et al.
Published: (2024)

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
by: Wen, Ruoyao, et al.
Published: (2026)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
by: Huang, Tiansheng, et al.
Published: (2025)

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
by: Nian, Yi, et al.
Published: (2025)

Defenses Against Prompt Attacks Learn Surface Heuristics
by: Li, Shawn, et al.
Published: (2026)

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
by: Luo, Weidi, et al.
Published: (2025)

Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
by: Tan, Rui Yang, et al.
Published: (2026)

WIPI: A New Web Threat for LLM-Driven Web Agents
by: Wu, Fangzhou, et al.
Published: (2024)

Onyx: Cost-Efficient Disk-Oblivious ANN Search
by: Rathee, Deevashwer, et al.
Published: (2026)

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
by: Liu, Xiaogeng, et al.
Published: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
by: Guo, Jiahe, et al.
Published: (2026)

Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security
by: Zhao, Wei, et al.
Published: (2025)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
by: Qi, Xiangyu, et al.
Published: (2024)

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
by: Ferrand, Jean-Charles Noirot, et al.
Published: (2025)

Measuring Safety Alignment Effects in Autonomous Security Agents
by: David, Isaac, et al.
Published: (2026)

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
by: Li, Hao, et al.
Published: (2025)

Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities
by: Lai, Evan, et al.
Published: (2025)

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
by: Kuznetsov, Daniel, et al.
Published: (2026)

JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
by: Luo, Weidi, et al.
Published: (2024)

LLM-Safety Evaluations Lack Robustness
by: Beyer, Tim, et al.
Published: (2025)

A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
by: Wu, Fangzhou, et al.
Published: (2024)

MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
by: Guo, Weiyang, et al.
Published: (2025)

What Matters For Safety Alignment?
by: Li, Xing, et al.
Published: (2026)

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
by: Vega, Jason, et al.
Published: (2025)