8 papers
Vision Language Model Helps Private Information De-Identification in Vision Data
Tiejin Chen, Pingzhi Li, Kaixiong Zhou +2
Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability. While various methods exist to enhance privacy in text-based applications, privacy…
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Tiejin Chen, Pingzhi Li, Kaixiong Zhou +2
Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Languag…
Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders
Het Patel, Tiejin Chen, Hua Wei +2
Large language models can be uncertain yet correct, or confident yet wrong, raising the question of whether their output-level uncertainty and their actual correctness are driven b…
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
Tiejin Chen, Xiaoou Liu, Vishnu Nandam +2
Preference-based alignment like Reinforcement Learning from Human Feedback (RLHF) learns from pairwise preferences, yet the labels are often noisy and inconsistent. Existing uncert…
Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models
Tiejin Chen, Kaishen Wang, Hua Wei
Jailbreaking methods, which induce Multi-modal Large Language Models (MLLMs) to output harmful responses, raise significant safety concerns. Among these methods, gradient-based app…
Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape
Tiejin Chen, Wenwang Huang, Linsey Pang +2
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classif…
When eBPF Meets Machine Learning: On-the-fly OS Kernel Compartmentalization
Zicheng Wang, Tiejin Chen, Qinrun Dai +3
Compartmentalization effectively prevents initial corruption from turning into a successful attack. This paper presents O2C, a pioneering system designed to enforce OS kernel compa…
Uncertainty Regularized Evidential Regression
Kai Ye, Tiejin Chen, Hua Wei +1
The Evidential Regression Network (ERN) represents a novel approach that integrates deep learning with Dempster-Shafer's theory to predict a target and quantify the associated unce…