Shouling Ji

TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models

STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model

When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeurons

Contextual and Seasonal LSTMs for Time Series Anomaly Detection

RiskAtlas: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation

HiddenGuard: Detecting and Interpreting NSFW Prompts in Text-to-Image Models through Uncovering Harmful Semantics

Angel or Demon: Investigating the Plasticity-Enhanced Strategies' Impact on Backdoor Threats in Deep Reinforcement Learning

Arcueid: Multi-trigger Cloud Shaping for Unified Backdoor Attack Paradigms

Trust the Process? Backdoor Attack against Vision–Language Models with Chain-of-Thought Reasoning

MASpi: A Unified Environment for Evaluating Prompt Injection Robustness in LLM-Based Multi-Agent Systems

Draining Your Account: A Stealthy Attack on API Billing in Multi-Agent Systems

The Case for Learned Provenance-based System Behavior Baseline