Xin Wang

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 PSR extsuperscript{2}, a novel static analysis framework that significantly improves the detection of atomicity violations in smart contracts by combining structural path searching with deep semantic reasoning.

The paper develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

The paper characterizes logging code security issues and benchmarks LLMs, finding that while LLMs can moderately detect these issues, they struggle significantly with reliably generating correct code repairs.

The paper proposes a scalable, helper-data-free open-set framework using an OpenGAN-based classifier to unify authentication for diverse and large populations of heterogeneous PUF-based IoT devices.

The paper proposes DUDE, a two-stage framework that significantly reduces the susceptibility of web agents to deceptive user interfaces by integrating deception detection into the agent's learning process.

DarkLLM introduces a novel framework that uses a Large Language Model (LLM) to translate natural language instructions into flexible, latent adversarial attack vectors, demonstrating a systemic vulnerability across diverse foundation models.

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime-aware diagnostic approach.

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robust rubric scoring.

AdaptR1 is a novel Reinforcement Learning framework that adaptively manages reasoning effort at every step of multi-hop Question Answering, significantly reducing unnecessary computational cost without sacrificing performance.

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent performance.

SentGuard introduces a novel sentence-level streaming guardrail that operates in parallel with LLM generation, achieving high detection rates of unsafe content early in the response while maintaining low false-positive rates.