2 citations · 3 across the 10 of their papers we have counts for
10 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…
TellOnce: Correcting Coding Agents Once, Improving Their Future Actions
Yujun Zhou, Kehan Guo, Haomin Zhuang +8
Interactive LLM agents increasingly work with users across tasks, yet remembering a previous correction does not ensure that the agent changes its behavior in the future. In a diag…
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4
Small language models (1.5B-4B parameters) offer low-cost, low-latency tool use but often produce plausible plans that fail during execution due to unavailable tools, missing argum…
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…
Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu +3
Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved documents. Existing detection meth…
FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
Youngsun Lim, Cusuh Ham, Pin-Yu Chen +1
Existing text-to-image (T2I) evaluation metrics mainly assess whether generated images align with information explicitly stated in the prompt, but often fail to capture factual req…
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…
Large Reasoning Models Learn Better Alignment from Flawed Thinking
ShengYun Peng, Pin-Yu Chen, Eric Smith +6
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about sa…
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…
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
ShengYun Peng, Pin-Yu Chen, Matthew Hull +1
Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, rece…