Real World eXploitation

Real-world exploitation research focuses on optimizing the balance between exploration (discovering new information) and exploitation (leveraging existing knowledge) across diverse domains. Current efforts concentrate on developing improved algorithms, such as modified swarm optimization and reinforcement learning techniques, to enhance efficiency and robustness in tasks ranging from optimizing engineering designs and navigating complex environments to identifying vulnerabilities in AI systems and improving machine learning model performance. This research is significant for advancing optimization methods, improving AI safety and security, and enabling more efficient and effective solutions in various fields, including robotics, cybersecurity, and healthcare.

Papers

November 7, 2024

Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models
Pete Janowczyk, Linda Laurier, Ave Giulietta, Arlo Octavia, Meade Cleti
Language Model Adversarial Attack Plain Sight Real World eXploitation Multimodal Generation Multi Modal Language Model Visual Pathway

November 6, 2024

Fair Exploration and Exploitation
Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
Fairness Constraint Real World eXploitation Contextual Bandit Problem Time Complexity

September 20, 2024

MRSO: Balancing Exploration and Exploitation through Modified Rat Swarm Optimization for Global Optimization
Hemin Sardar Abdulla, Azad A. Ameen, Sarwar Ibrahim Saeed, Ismail Asaad Mohammed, Tarik A. Rashid
Optimization Purpose Global Optimization Efficient Optimization Real World eXploitation Exploration Performance Swarm Optimization

August 27, 2024

Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data
Lintao Xu, Chaohui Wang
Synthetic Data Real World eXploitation 2 Dimensional Image Unseen Occlusion Occlusion Reasoning

July 10, 2024

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems
Chashi Mahiul Islam, Shaeke Salman, Montasir Shams, Xiuwen Liu, Piyush Kumar
Vision Language Model Robot Navigation Vision and Language Navigation Language Navigation Real World eXploitation Malicious Attack

June 2, 2024

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang
LLM Agent Security Vulnerability Real World eXploitation Long Horizon Planning Common Vulnerability Zero Day Agent Planning Team Affiliation

May 14, 2024

Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation
Riyad Bin Rafiq, Weishi Shi, Mark V. Albert
Continual LEArning Hand Gesture Intermediate Latent Real World eXploitation Gesture Data Motor Impairment

May 7, 2024

Inferring Discussion Topics about Exploitation of Vulnerabilities from Underground Hacking Forums
Felipe Moreno-Vera
Security Vulnerability Latent Dirichlet Allocation Discussion Paper Real World eXploitation Latent Topic Hacker Forum

May 4, 2024

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
JaeYoon Kim, Junyu Xuan, Christy Liang, Farookh Hussain
Multi Agent Decoupling Coefficient Unsupervised Pre Training Real World eXploitation Exploration Method Successor Feature

April 11, 2024

WESE: Weak Exploration to Strong Exploitation for LLM Agents
Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen
Open World Graph Based LLM Agent Task Specific Knowledge Real World eXploitation Exploration Task Inefficient Exploration

April 6, 2024

Exhaustive Exploitation of Nature-inspired Computation for Cancer Screening in an Ensemble Manner
Xubin Wang, Yunhe Wang, Zhiqing Ma, Ka-Chun Wong, Xiangtao Li
Ensemble Learning Diverse Ensemble Gene Expression Data Real World eXploitation Ensemble Diversity Cancer Screening

March 21, 2024

On the exploitation of DCT statistics for cropping detectors
Claudio Vittorio Ragaglia, Francesco Guarnera, Sebastiano Battiato
Image Processing Discrete Cosine Transform Real World eXploitation Crop Segmentation Image Assessment Resolution Image Classification

March 2, 2024

Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding
Ha-Thanh Nguyen, Ken Satoh
Reinforcement Learning Medical LLM Negation Detection Real World eXploitation Exploration Performance Explanatory Feedback Logical Reasoning Ability Soft Q Learning Natural Language Negation

February 8, 2024

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Guangyu Shen, Siyuan Cheng, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang
Large Language Model Open Source Large Language Model Real World eXploitation

February 3, 2024

On the Exploitation of DCT-Traces in the Generative-AI Domain
Orazio Pontorno, Luca Guarnera, Sebastiano Battiato
Generative Question Deep Fake Deepfake Detector Joint Photographic Expert Group Discrete Cosine Transform Real World eXploitation Deepfake Image Human Readable FingerPrint

January 10, 2024

AI Art is Theft: Labour, Extraction, and Exploitation, Or, On the Dangers of Stochastic Pollocks
Trystan S. Goetze
Generative AI Image Generation Generative Artificial Intelligence AI Generated Image Real World eXploitation Co Worker AI Art

January 6, 2024

Malla: Demystifying Real-world Large Language Model Integrated Malicious Services
Zilong Lin, Jian Cui, Xiaojing Liao, XiaoFeng Wang
Language Model Real World eXploitation Black Box LLM Threat Landscape

December 18, 2023

Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure
Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse
Reward Function Sample Efficient Reinforcement Learning Real World eXploitation Finite State Machine Adaptive Machine Automaton Model

October 31, 2023

Performance Improvement in Multi-class Classification via Automated Hierarchy Generation and Exploitation through Extended LCPN Schemes
Celal Alagoz
Performance Improvement Multi Class Classification Classification Performance Hierarchical Classification Real World eXploitation Multi Class Classification Task

October 12, 2023

Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning
Valentina Zangirolami, Matteo Borrotti
Reinforcement Learning Deep Reinforcement Learning High Uncertainty Anticipation Environment Exploration Autonomous Agent Real World eXploitation Exploration Exploitation Trade

Real World eXploitation

Papers

Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models

Fair Exploration and Exploitation

MRSO: Balancing Exploration and Exploitation through Modified Rat Swarm Optimization for Global Optimization

Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation

Inferring Discussion Topics about Exploitation of Vulnerabilities from Underground Hacking Forums

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features

WESE: Weak Exploration to Strong Exploitation for LLM Agents

Exhaustive Exploitation of Nature-inspired Computation for Cancer Screening in an Ensemble Manner

On the exploitation of DCT statistics for cropping detectors

Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia

On the Exploitation of DCT-Traces in the Generative-AI Domain

AI Art is Theft: Labour, Extraction, and Exploitation, Or, On the Dangers of Stochastic Pollocks

Malla: Demystifying Real-world Large Language Model Integrated Malicious Services

Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure

Performance Improvement in Multi-class Classification via Automated Hierarchy Generation and Exploitation through Extended LCPN Schemes

Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning