Inherent Vulnerability

Inherent vulnerability research focuses on identifying and mitigating weaknesses within various systems, particularly in artificial intelligence and software. Current research emphasizes vulnerabilities in deep learning frameworks, large language models (LLMs), and data pipelines, employing techniques like outlier detection, code analysis, and adversarial attacks to assess and improve system robustness. This work is crucial for enhancing the security and reliability of AI systems and software, impacting fields ranging from cybersecurity to data management and ethical AI development. Understanding and addressing these vulnerabilities is essential for building trustworthy and dependable technologies.

Papers

October 17, 2024

Leveraging Fine-Tuned Language Models for Efficient and Accurate Smart Contract Auditing
Zhiyuan Wei, Jing Sun, Zijian Zhang, Xianhao Zhang, Meng Li
High Efficiency Smart Contract Fine Tuned Language Model High Accuracy Inherent Vulnerability Domain Knowledge Distillation

June 12, 2024

On Security Weaknesses and Vulnerabilities in Deep Learning Systems
Zhongzheng Lai, Huaming Chen, Ruoxi Sun, Yu Zhang, Minhui Xue, Dong Yuan
Security Vulnerability Deep Learning System Software Vulnerability Common Vulnerability Inherent Vulnerability Vulnerability Pattern

March 22, 2024

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers
Sivana Hamer, Marcelo d'Amorim, Laurie Williams
ChatGPT Generated Conversation Generative Artificial Intelligence Real World Code Security Vulnerability Stack Overflow Copy Paste Inherent Vulnerability SAfER Instruct Insecure Code

March 12, 2024

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma
Code Completion Safety Alignment Generalization Problem Inherent Vulnerability

February 16, 2024

Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks
Jun-Jie Zhang, Deyu Meng
Adversarial Attack General Analysis Integral Role Black Box Random Perturbation Inherent Vulnerability Network Attack

January 17, 2024

A Blockchain-based Model for Securing Data Pipeline in a Heterogeneous Information System
MN Ramahlosi, Y Madani, A Akanbi
Heterogeneous System Inherent Vulnerability

January 15, 2024

Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection
Imam Nur Bani Yusuf, Lingxiao Jiang
Deep Learning Human Instruction Instruction Fine Tuning Inherent Vulnerability

January 11, 2024

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Shuai Zhao, Meihuizi Jia, Luu Anh Tuan, Fengjun Pan, Jinming Wen
Large Language Model Language Model Context Learning Backdoor Attack Attack Success Rate Inherent Vulnerability

December 12, 2023

WE economy: Potential of mutual aid distribution based on moral responsibility and risk vulnerability
Takeshi Kato
Inherent Vulnerability Human Society Redistribution Mechanism Wealth Inequality Wealth Distribution Moral Responsibility

December 4, 2023

A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, Yue Zhang
Large Language Model Timely Survey Medical LLM Privacy Policy Security Related Security Vulnerability Extraction Attack Inherent Vulnerability

October 24, 2023

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Liu Kost, Christopher Carnahan, Jordan Boyd-Graber
Large Language Model Chatbot Response Adversarial Prompt Prompt Attack Inherent Vulnerability

May 25, 2023

Assessing the Spatial Structure of the Association between Attendance at Preschool and Childrens Developmental Vulnerabilities in Queensland Australia
wala Draidi Areed, Aiden Price, Kathryn Arnett, Helen Thompson, Reid Malseed, Kerrie Mengersen
Demographic Attribute Spatial Structure Inherent Vulnerability Developmental Trajectory Attendance Management

April 3, 2023

OutCenTR: A novel semi-supervised framework for predicting exploits of vulnerabilities in high-dimensional datasets
Hadi Eskandari, Michael Bewong, Sabih ur Rehman
High Dimensional Outlier Detection Security Vulnerability Vulnerability Data Inherent Vulnerability Novel Semi Supervised K$ Center

January 12, 2023

Against Algorithmic Exploitation of Human Vulnerabilities
Inga Strümke, Marija Slavkovik, Clemens Stachl
Recommender System Latent Vulnerability Inherent Vulnerability Learning Based Recommender System

September 16, 2022

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding, Zhepeng Cen, Bo Li, Ding Zhao
Reinforcement Learning Native Robustness Stronger Generalizability Human SAFETY Inherent Vulnerability

April 11, 2022

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu
Pre Trained Language Model Prompt Based Learning Inherent Vulnerability Adversarial Trigger

Inherent Vulnerability

Papers

Leveraging Fine-Tuned Language Models for Efficient and Accurate Smart Contract Auditing

On Security Weaknesses and Vulnerabilities in Deep Learning Systems

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks

A Blockchain-based Model for Securing Data Pipeline in a Heterogeneous Information System

Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning

WE economy: Potential of mutual aid distribution based on moral responsibility and risk vulnerability

A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Assessing the Spatial Structure of the Association between Attendance at Preschool and Childrens Developmental Vulnerabilities in Queensland Australia

OutCenTR: A novel semi-supervised framework for predicting exploits of vulnerabilities in high-dimensional datasets

Against Algorithmic Exploitation of Human Vulnerabilities

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm