Kun Wang

This survey systematically reviews resource consumption threats in large language models (LLMs) to provide a unified view of the problem landscape, from threat induction to mitigation.

STEP introduces a novel, black-box, retraining-free detector that profiles audio samples using dual perturbation branches to detect backdoor attacks by exploiting the characteristic instability of hidden triggers.

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.

The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models can be hijacked with high success rates.

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projector, causing a measurable semantic shift in poisoned inputs.

The paper proposes FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLLMs).

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and improve robustness.

HoliTok introduces a novel continuous holistic tokenization model that provides a unified, high-fidelity latent representation for simultaneously supporting both speech generation and speech understanding tasks.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

This paper proposes a new method for agentic Reinforcement Learning called Agentic Procedural Policy Optimization (APPO) that improves tool-use capabilities by assigning credit to fine-grained decision points.