8 citations · 25 across the 12 of their papers we have counts for
13 papers
MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis
Bo Shao, Yihan Ma, Yiting Qu +2
Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong dependence on contextual inform…
EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
Yiting Qu, Ziqing Yang, Chi Cui +3
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be dire…
GEO-Flag: Detecting and Measuring GEO-Optimized Web Content
Junjie Chu, Ye Leng, Mingjie Li +3
Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized…
Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation
Ye Leng, Junjie Chu, Yiting Qu +3
Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda…
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Junjie Chu, Yiting Qu, Ye Leng +4
Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a sub…
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Yiting Qu, Ziqing Yang, Yihan Ma +3
Recent advances in text-to-image diffusion models have enabled the creation of a new form of digital art: optical illusions--visual tricks that create different perceptions of real…
Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Yiting Qu, Michael Backes, Yang Zhang
Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However,…
HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns
Xinyue Shen, Yixin Wu, Yiting Qu +3
Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a…
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Boyang Zhang, Yicong Tan, Yun Shen +4
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can exten…
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
Yiting Qu, Xinyue Shen, Yixin Wu +3
With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images.…
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Xinlei He, Savvas Zannettou, Yun Shen +1
The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of…
Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots
Wai Man Si, Michael Backes, Jeremy Blackburn +4
Chatbots are used in many applications, e.g., automated agents, smart home assistants, interactive characters in online games, etc. Therefore, it is crucial to ensure they do not b…
On Xing Tian and the Perseverance of Anti-China Sentiment Online
Xinyue Shen, Xinlei He, Michael Backes +3
Sinophobia, anti-Chinese sentiment, has existed on the Web for a long time. The outbreak of COVID-19 and the extended quarantine has further amplified it. However, we lack a quanti…