8 papers
When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting
Binyan Xu, Xilin Dai, Fan Yang +1
AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred. Providers often disclaim consequ…
From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
Binyan Xu, Fan Yang, Xilin Dai +2
Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model re…
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
Fan Yang, Binyan Xu, Di Tang +1
GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph…
Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review
Binyan Xu, Fan Yang, Xilin Dai +1
Peer review at ML conferences increasingly relies on reviewer scores as the primary decision instrument. As submissions have scaled from thousands to tens of thousands per year, no…
Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection
Fan Yang, Binyan Xu, Di Tang +1
Provenance-based intrusion detection has emerged as a promising approach for analyzing complex attack behaviors through system-level provenance graphs. However, existing defense me…
Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
Wenkai Li, Fan Yang, Shaunak A. Mehta +1
Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering e…