6 papers
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Zihao Wang, Yiming Li, Yutong Wu +8
LLM-based web agents are increasingly deployed in real-world settings such as e-commerce, where they interact extensively with untrusted web content while executing actions that ca…
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Yujun Zhou, Kehan Guo, Haomin Zhuang +8
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated…
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4
Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style tool use requires more than isolated function calling: an agent must discover…
Backdooring Masked Diffusion Language Models
Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou +3
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdo…
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
Yue Huang, Haomin Zhuang, Jiayi Ye +6
Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less us…
Shape it Up! Restoring LLM Safety during Finetuning
ShengYun Peng, Pin-Yu Chen, Jianfeng Chi +2
Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A com…