Papers by Haibo Jin
Building a Broad Infrastructure for Uniform Meaning Representations (2024.lrec-main)
Copied to clipboard
Julia Bonn, Matthew J. Buchholz, Jayeol Chun, Andrew Cowell, William Croft, Lukas Denk, Sijia Ge, Jan Hajič, Kenneth Lai, James H. Martin, Skatje Myers, Alexis Palmer, Martha Palmer, Claire Benet Post, James Pustejovsky, Kristine Stenzel, Haibo Sun, Zdeňka Urešová, Rosa Vallejos, Jens E. L. Van Gysel, Meagan Vigus, Nianwen Xue, Jin Zhao
| Challenge: | This paper reports the first release of the UMR data set for six languages . it includes annotations for six different languages that vary greatly in terms of their linguistic properties and resource availability. |
| Approach: | They report the first release of the UMR data set for six languages . they describe on-going efforts to enlarge the data set and extend it to other languages - including Navajo, Navájo, and Sanapaná . |
| Outcome: | The first release of the UMR data set includes annotations for six languages . the language dataset is available for free and can be extended to other languages if needed . |
AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search (2026.findings-acl)
Copied to clipboard
| Challenge: | prompt stealing is a new form of attack that aims to reconstruct high-value prompts that guide music generation. |
| Approach: | They propose a method to steal music prompts from audio domains using a black-box attack framework. |
| Outcome: | The proposed method recovers prompts with high textual consistency to the ground truth while maintaining strong perceptual similarity to the target recordings. |
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing white-box jailbreak methods require full model accessibility and require computational costs. |
| Approach: | They propose a black-box jailbreak attack using Zeroth-Order optimization using ZO-SPSA. |
| Outcome: | The proposed method achieves highest jailbreak success rate on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4. |
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has shown that intent detection enhances LLMs’ moderation guardrails, but the robustness of these guardrail mechanisms under malicious manipulations remains under-explored. |
| Approach: | They propose a two-stage intent-based prompt-refinement framework that first transforms harmful inquiries into structured outlines and further reframes them into declarative-style narratives. |
| Outcome: | The proposed framework outperforms several cutting-edge jailbreak methods and evades even advanced Intent Analysis (IA) and Chain-of-Thought (CoT)-based defenses. |
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as finance where unsafe behavior can lead to serious regulatory risks. |
| Approach: | They propose a black-box multi-turn risk-concealed redteaming framework that progressively conceals surface-level risk while exploiting regulatory-violating behaviors. |
| Outcome: | Experiments on nine widely used LLMs show that the proposed framework achieves 93.19% average attack success rate (ASR) and improves the average ASR to 95.00%. |
Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing jailbreaks against large audio-language models fall into two categories . early work converted text-based prompts into synthetic speech, while subsequent work introduced minor acoustic variations such as accent shifts, phonetic spellings, or stress patterns. |
| Approach: | They propose a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. |
| Outcome: | The proposed attack exploits structural and acoustic properties of a text-to-audio model . it achieves 98.26% success rate, significantly exceeding baselines for text-based models . |