Ting Liu

The paper introduces BadStyle, a novel backdoor attack framework that generates natural, stealthy poisoned samples using LLMs to compromise various LLMs with high success rates and robust activation.

This paper introduces UPAttack, a novel threat model demonstrating that focusing on explicit usability requirements can cause LLMs to generate insecure code by neglecting implicit security constraints, and proposes U-SPLOIT to automate this attack.

DeepTool introduces a novel Process-Supervised Reinforcement Learning framework to enhance Tool-Integrated Reasoning by explicitly supervising and rewarding intermediate, interleaved deliberation steps during sequential tool use.

This paper proposes HCP, a Handle-Capability Protocol runtime for MCP-style agent systems, which implements eight execution-control invariants to enhance security while preserving MCP-like workflows.

This paper proposes AMLGuard, a semantic-aware AML framework for account-based blockchains that tracks illicit fund flows in complex DeFi transactions using rule-based analysis and large language model reasoning.

This paper proposes TrapHunter, a framework to identify deceptive trap tokens in standardized contracts using intent deviation analysis and dynamic validation.