7 papers · 1 filter
IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
Nicole Geumheon Liu, Haeun Jang, Yonghyun Jun +1
Large Language Models (LLMs) often fail to maintain instruction hierarchies (IH) when processing multi-source inputs with varying role-level priorities, paradoxically adhering to l…
Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models
Haeun Jang, Hwan Chang, Hwanhee Lee
The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined policies that dictate information di…
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang, Yonghyun Jun, Hwanhee Lee
The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major t…
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
Hwan Chang, Yumin Kim, Yonghyun Jun +1
As Large Language Models (LLMs) are increasingly deployed in sensitive domains such as enterprise and government, ensuring that they adhere to user-defined security policies within…
Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization
Joonho Yang, Seunghyun Yoon, Hwan Chang +2
Large Language Models (LLMs) have significantly advanced text generation capabilities, including tasks like summarization, often producing coherent and fluent outputs. However, fai…
Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
Hwan Chang, Hwanhee Lee
Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these ri…