54 citations · 121 across the 18 of their papers we have counts for
19 papers
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan +7
We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multi…
Persistent Pre-Training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov +5
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training dat…
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Samuele Poppi, Zheng-Xin Yong, Yifei He +4
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily remove…
Backtracking Improves Generation Safety
Yiming Zhang, Jianfeng Chi, Hailey Nguyen +4
Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context o…
BadMerging: Backdoor Attacks Against Model Merging
Jinghuai Zhang, Jianfeng Chi, Zheng Li +3
Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approa…
The Llama 3 Herd of Models
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri +556
Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models th…
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Hakan Inan, Kartikeya Upasani, Jianfeng Chi +8
We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool f…
Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
Kunlin Cai, Jinghuai Zhang, Zhiqing Hong +5
As location-based services (LBS) have grown in popularity, more human mobility data has been collected. The collected data can be used to build machine learning (ML) models for LBS…
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
Xiaotian Han, Jianfeng Chi, Yu Chen +4
This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods. Ensuring fairness in machine learning is import…
PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English
Jianfeng Chi, Wasi Uddin Ahmad, Yuan Tian +1
Privacy policies provide individuals with information about their rights and how their personal information is handled. Natural language understanding (NLU) technologies can suppor…
Conditional Supervised Contrastive Learning for Fair Text Classification
Jianfeng Chi, William Shand, Yaodong Yu +3
Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned…
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies
Md Rizwan Parvez, Jianfeng Chi, Wasi Uddin Ahmad +2
Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user qu…
Towards Return Parity in Markov Decision Processes
Jianfeng Chi, Jian Shen, Xinyi Dai +3
Algorithmic decisions made by machine learning models in high-stakes domains may have lasting impacts over time. However, naive applications of standard fairness criterion in stati…
Understanding and Mitigating Accuracy Disparity in Regression
Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon +1
With the widespread deployment of large-scale prediction systems in high-stakes domains, e.g., face recognition, criminal justice, etc., disparity in prediction accuracy between di…
Intent Classification and Slot Filling for Privacy Policies
Wasi Uddin Ahmad, Jianfeng Chi, Tu Le +3
Understanding privacy policies is crucial for users as it empowers them to learn about the information that matters to them. Sentences written in a privacy policy document explain…
PolicyQA: A Reading Comprehension Dataset for Privacy Policies
Wasi Uddin Ahmad, Jianfeng Chi, Yuan Tian +1
Privacy policy documents are long and verbose. A question answering (QA) system can assist users in finding the information that is relevant and important to them. Prior studies in…
Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
Fnu Suya, Jianfeng Chi, David Evans +1
We study adversarial examples in a black-box setting where the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial ex…
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
Han Zhao, Jianfeng Chi, Yuan Tian +1
Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimi…
Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
Jianfeng Chi, Emmanuel Owusu, Xuwang Yin +4
We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep networ…